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

Abstract

To properly determine a sales page of a commodity to be recommended to a user.SOLUTION: An information processing apparatus acquires a list of sales page identification information identifying each sales page for one or more commodities associated with each user, converts the list of sales page identification information into a list of commodity identification information identifying a commodity, generates a recommended commodity list including recommended commodity identification information identifying each of one or more commodities to be recommended to the user, based on the list of commodity identification information, determines a sales page for each of the one or more commodities to be recommended to the user, based on one or more pieces of recommended commodity identification information included in the recommended commodity list.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to a technique for determining a sales page of a product recommended to a user.

Background Art

[0002] In recent years, e-commerce (Electronic Commerce (EC)) that sells products online using the Internet has been actively carried out. Such EC is implemented via an EC site such as an EC mall (mall-type EC site) where multiple stores develop a shopping mall online. By accessing the EC site from a portable terminal such as a PC (Personal Computer) or a smartphone, a user can view and purchase desired products without actually visiting multiple stores and without worrying about time.

[0003] For the purpose of promoting sales on an EC site, a technique has been proposed to identify products that a user is interested in from the action history of the user on the sales page of the product, such as the purchase history and browsing history of the user, and to determine products to be recommended (recommended) to the user based on the identified products. For example, Patent Document 1 discloses determining, as recommended products, a second product that has a predetermined relationship with a first product identified based on the purchase history of a user.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] When determining recommended products for a user based on their action history on a sales page, it is crucial to appropriately associate action information with product identification information to identify products the user is interested in. In e-commerce marketplaces, if the same product is sold by multiple stores, that same product may be displayed and sold on different sales pages for each store. Even if the product is the same, if it is sold on different sales pages, there was a possibility that the action information would not be appropriately associated with the product identification information. In other words, the user's action information on these different sales pages would not be associated with the same product identification information, but with different product identification information, which could lead to an inappropriate association between the action information and the product identification information. As a result, there was a risk that the sales page for the recommended product could not be appropriately determined for the user.

[0006] This invention has been made in view of the above problems, and aims to provide a technology for appropriately determining the sales page of a product to recommend to a user. [Means for solving the problem]

[0007] To solve the above problems, one aspect of the information processing apparatus according to the present invention includes: an acquisition unit that acquires a list of sales page identification information that identifies each of the sales pages of one or more products associated with each user; a conversion unit that converts the list of sales page identification information into a list of product identification information that identifies products; a generation unit that generates a list of recommended products that includes recommended product identification information that identifies each of the one or more products to be recommended to each user based on the list of product identification information; and a determination unit that determines the sales page of each of the one or more products to be recommended to each user based on one or more of the recommended product identification information included in the recommended product list.

[0008] To solve the above problems, one aspect of the information processing method according to the present invention includes: an acquisition step of obtaining a list of sales page identification information that identifies each of the sales pages of one or more products associated with each user; a conversion step of converting the list of sales page identification information into a list of product identification information that identifies products; a generation step of generating a recommended product list that includes recommended product identification information that identifies each of the one or more products recommended to each user based on the list of product identification information; and a determination step of determining the sales page of each of the one or more products recommended to each user based on one or more of the recommended product identification information included in the recommended product list.

[0009] To solve the above problems, one aspect of the information processing program according to the present invention causes a computer to perform the following: an acquisition process to acquire a list of sales page identification information that identifies each of the sales pages of one or more products associated with each user; a conversion process to convert the list of sales page identification information into a list of product identification information that identifies products; a generation process to generate a recommended product list that includes recommended product identification information that identifies each of the one or more products recommended to each user, based on the list of product identification information; and a determination process to determine the sales page of each of the one or more products recommended to each user, based on one or more of the recommended product identification information included in the recommended product list. [Effects of the Invention]

[0010] According to the present invention, it becomes possible to appropriately determine the sales page for the product to recommend to the user. The objects, embodiments, and effects of the present invention described above, as well as any other objects, embodiments, and effects of the present invention not described above, can be understood by those skilled in the art from the following embodiments for carrying out the invention by referring to the accompanying drawings and the claims. [Brief explanation of the drawing]

[0011] [Figure 1] Figure 1 shows an example of the configuration of an information processing system according to an embodiment. [Figure 2]FIG. 2 shows a functional configuration example of the information processing apparatus according to the first embodiment. [Figure 3] FIG. 3 shows an example of a list of sales page IDs in time series. [Figure 4] FIG. 4 shows a hardware configuration example of the information processing apparatus according to the embodiment. [Figure 5] FIG. 5 is a flowchart of the processing executed by the information processing apparatus according to the embodiment. [Figure 6] FIG. 6 shows an example of a list of sales page IDs for each user. [Figure 7] FIG. 7 shows an example of a list of product IDs for each user. [Figure 8] FIG. 8 shows an example of a list of recommended product IDs for each user. [Figure 9] FIG. 9 shows an example of a list of recommended sales page IDs for each user. [Figure 10] FIG. 10 shows a functional configuration example of the information processing apparatus according to the second embodiment. [Figure 11] FIG. 11 is a flowchart of the genre determination process according to the second embodiment. [Figure 12] FIG. 12 is a conceptual diagram showing the data flow for determining the top 4 genre IDs. [Figure 13A] FIG. 13A shows an example of a screen including a sales page for selling a plurality of products in an EC mall. [Figure 13B] FIG. 13B shows an example of a screen including a sales page for selling a product in an EC mall. [Figure 13C] FIG. 13C shows another example of a screen including a sales page for selling a plurality of products in an EC mall. [Figure 14] FIG. 14 shows a functional configuration example of the information processing apparatus according to the fourth embodiment. [Figure 15] FIG. 15 shows another example of a list of product IDs for each user.

BEST MODE FOR CARRYING OUT THE INVENTION

[0012] Hereinafter, embodiments for implementing the present invention will be described in detail with reference to the accompanying drawings. Among the components disclosed below, those having the same function are denoted by the same reference numerals, and the description thereof will be omitted. The embodiments disclosed below are an example of means for realizing the present invention, and should be appropriately modified or changed according to the configuration of the apparatus to which the present invention is applied and various conditions. The present invention is not limited to the following embodiments. Also, not all combinations of features described in this embodiment are essential for the solution means of the present invention.

[0013] <First Embodiment> [Configuration of Information Processing System] FIG. 1 shows a configuration example of an information processing system 1 according to this embodiment. The information processing system 1 includes an information processing apparatus 10, an EC site server 11, and a user apparatus 12. The information processing apparatus 10, the EC site server 11, and the user apparatus 12 are configured to be communicable with each other via a network 13. The network 13 can include, in addition to the Internet, an intranet, a LAN (Local Area Network), a WAN (Wide Area Network), a mobile communication network, and the like. In FIG. 1, one user apparatus 12 is illustrated, but the information processing system 1 is configured to have a plurality of user apparatuses having the same function as the user apparatus 12. In the present disclosure, the plurality of user apparatuses are collectively referred to as the user apparatus 12. Also, the user apparatus 12 is operated by a user 14. In the present disclosure, the terms "user apparatus" and "user" may be understood synonymously.

[0014] The EC site server 11 is a server device that operates an e-commerce mall (mall-type e-commerce site) where multiple stores operate an online shopping mall. Specifically, the EC site server 11 operates an e-commerce mall that operates through sales pages (web pages) of products sold by multiple stores (merchants). The EC site server 11 accepts access from user devices 12 via the network 13 and can provide various services related to shopping in the e-commerce mall to users 14. For example, when a user accesses the e-commerce mall and takes an action such as purchasing or browsing on the sales page of a desired product, the EC site server 11 provides services related to that product to the user 14. In addition, the EC site server 11 can acquire (collect) and manage information about the sales page of the product on which the user 14 took an action in the e-commerce mall. Note that the EC site server 11 is not limited to a server device and may be implemented using a mainframe or the like.

[0015] User device 12 is operated by user 14 to access the EC site server 11 and receive various services on the EC mall provided by the EC site server 11. For example, user 14 can operate user device 12 to access the EC mall and view and purchase various product sales pages offered on the EC mall. When using services on the EC mall, user 14 registers information about user 14 (hereinafter also referred to as user attributes). For example, user 14 sets a user ID (user identification information) that identifies user 14, which is linked to user attributes, and logs in using this user ID to use services on the EC mall. By setting a user ID, user 14 can use the EC mall services even from a user device other than user device 12 connected to network 13.

[0016] User attributes include factual attributes of the user. These factual attributes include the IP address of the user's device, the user's address and name, the user's credit card number, and the user's demographic information (such as gender, age, residential area, occupation, family structure, etc.). Furthermore, user factual attributes may include registration numbers and registered names when using web services, including e-commerce malls (and related web services). Additionally, user factual attributes may include usage history, search history, purchase history (including purchase results), and information regarding points that can be accumulated through service use. Thus, user factual attributes can include any information related to the user's device or the user themselves, as well as information regarding the use of web services, including e-commerce malls. Furthermore, user attributes may include estimated user attributes. These estimated user attributes can be estimated based on the user's factual attributes, for example, by a trained user attribute estimation model. Estimated user attributes may include preferences for products of interest and lifestyle.

[0017] The user device 12 is, for example, a smartphone or tablet, and is configured to communicate with the EC site server 11 and the information processing device 10 via the network 13. The user device 12 has a display unit (display surface) such as a liquid crystal display, and the user 14 can perform various operations using the GUI (Graphical User Interface) equipped on the display unit. These operations include various operations on content such as images displayed on the screen, such as tapping, sliding, and scrolling using a finger or stylus. The user device 12 may also have a separate display unit.

[0018] The information processing device 10 acquires information about product sales pages collected by the EC site server 11 and determines the sales pages of products to recommend to user 14 based on this information. Specifically, the information processing device 10 first acquires a list of sales page IDs that identify the sales pages of products associated with user 14, and converts this list of sales page IDs into a list of product IDs that identify products. Next, the information processing device 10 generates a recommended product list that includes recommended product IDs that identify products to recommend to user 14 based on this list of product IDs, and determines the sales pages of products to recommend to user 14 based on these recommended product IDs. The information on the determined product sales pages is provided to the EC site server 11, and the EC site server 11 can provide the sales pages to the user device 12 according to this information. Note that in Figure 1, the information processing device 10 and the EC site server 11 are configured as separate devices, but the information processing device 10 may be configured to include the functions of the EC site server 11.

[0019] Figure 13A shows an example of screen 1300, which includes multiple sales pages in an e-commerce mall provided by the e-commerce site server 11. Each of the multiple sales pages is managed and operated by a different store (merchant). Therefore, each of the multiple sales pages is associated with the store of the product sold on that sales page. In screen 1300, each sales page includes an image of the product being sold and information about that product (description, price, etc.). Taking sales page 1302 as an example, sales page 1302 is a sales page that sells product 1301. Product 1301 is specifically an image of the product sold on sales page 1302, but in this disclosure, this image is referred to as the product. Furthermore, the image on the sales page only needs to be an image that describes the product being sold.

[0020] [Functional Configuration of Information Processing Equipment] Figure 2 shows an example of the functional configuration of the information processing device 10 according to this embodiment. The information processing device 10, as an example of its functional configuration, includes a sales page ID (sales page identification information) acquisition unit 201, a product ID (product identification information) list generation unit 202, a recommended product list generation unit 203, a sales page determination unit 204, a table storage unit 210, and a learning model storage unit 220.

[0021] The table storage unit 210 is configured to store a product conversion table 211 for converting sales page IDs to product IDs. The product conversion table 211 is a table that associates product IDs, which identify products sold by the e-commerce mall, with sales page IDs, which identify one or more sales pages on which those products are sold. The same product is assigned to the same product. Even the same product may be sold on different sales pages, so in the product conversion table 211, one product ID may be associated with multiple different sales page IDs. In this embodiment, it is assumed that one sales page ID will not be associated with multiple product IDs.

[0022] The learning model memory unit 220 is configured to store the trained feature vector extraction model 221. The feature vector extraction model 221 is a machine learning model that extracts (derives) a vector representation of a user with a given user ID based on past actions associated with that user ID. Specifically, the feature vector extraction model 221 is a machine learning model configured to take a list of product IDs of products that the user with that user ID has previously performed actions on (for example, information indicating such a list) as input and output a vector representation of the user with that user ID. This vector representation corresponds to a vectorized representation of the product IDs that the user has shown interest in. The feature vector extraction model 221 is configured to be either MF (Matrix Factorization) based or Natural Language Processing (NLP) based. The MF-based model is a model that decomposes an evaluation value matrix consisting of m (number of rows) × n (number of columns) (where m and n are integers greater than or equal to 2) into two matrices by reducing the dimensionality through collaborative filtering. The NLP-based model is a natural language processing model that converts words into vector representations, such as Word2Vec. The feature vector extraction model 221 is retrained as needed by a processing unit (not shown) in the information processing device 10 or by an external device.

[0023] Furthermore, the information processing device 10 may not be provided in a single device, but rather divided and provided in multiple devices. For example, a part of the information processing device 10 may be provided in an external server device such as an e-commerce site server 11. In this case, the functions shown in this embodiment are realized through cooperation between the information processing device 10 and the external server device.

[0024] Figure 2 also shows an example of the functional configuration of the EC site server 11 related to this embodiment. The EC site server 11 is connected to the information processing device 10 via a network 13. In Figure 2, the EC site server 11 has, as a functional configuration related to this embodiment, an EC mall operation unit 231, an evaluation index derivation unit 232, a sales page ID database 240, and an evaluation index database 250.

[0025] The EC Mall Operation Unit 231 operates an EC mall where multiple stores sell products online. For example, the EC Mall Operation Unit 231 can create multiple sales pages based on product information provided by multiple stores and provide them to user devices 12 connected via the network 13. The EC Mall Operation Unit 231 can also provide services to user devices 12 according to the type of action taken on the product sales pages by the user devices 12. The EC Mall Operation Unit 231 can also provide the user devices 12 with sales pages instructed by the information processing device 10. When a predetermined action is performed on a product sales page by a user device 12, the EC Mall Operation Unit 231 stores a sales page ID associated with the user ID in the sales page ID database 240. An example of a sales page ID will be described later with reference to Figure 3. The Evaluation Indicator Derivation Unit 241 derives evaluation indicators (marketing indicators) associated with the sales pages in the EC mall provided by the EC Mall Operation Unit 231. The evaluation metric represents an evaluation metric for the products sold on the sales page and the stores (merchants) that sell those products, and may include the conversion rate (CVR) for the sales page. In this embodiment, a conversion in CVR is assumed to be a purchase of a product, but in other embodiments, it may be a click on the product. The evaluation metric may also include user ratings of the sales page and the ranking of those ratings (ranking). These ratings may include numerical representations of user evaluations, comments, and recommendations for at least one of the sales page, store, or product.

[0026] The EC Mall Operations Unit 231 adds a sales page ID to the list of sales page IDs stored in the sales page ID database 240 in chronological order each time a predetermined action is performed by a user on a product sales page in the EC Mall. In other words, a list of sales page IDs is generated each time the predetermined action is performed. The list of sales page IDs stored in the sales page ID database 240 will be hereinafter referred to as the chronological sales page ID list. Figure 3 shows an example of the chronological sales page ID list 30 stored in the sales page ID database 240. The chronological sales page ID list 30 is a list of sales page IDs collected each time a predetermined action is performed by three users on the sales pages of multiple products in the EC Mall. As an example, the chronological sales page ID list 30 is configured such that each column contains the components of User ID 301, Sales Page ID 302, Action Type 303, Action Date and Time 304, and Identifying Genre ID (Genre Identification Information) 305. Genre ID 305 is the genre of products sold on the sales page identified by sales page ID 302, and is associated with each product page.

[0027] User ID 301 is information that identifies each of the three users, and is one of UID_1, UID_2, and UID_3. User attributes are associated with each UID in User ID 301. For example, UID_1 is associated with the user attributes registered by the user identified by UID_1 when using the EC mall service. Sales page ID 302 is information that identifies the sales page (web page). Sales page ID 302 consists of a string that identifies the sales page of a product, for example, and may be a string as shown in Figure 3, or it may be a URL (Uniform Resource Locator). Action type 303 indicates the type of predetermined action on the sales page of a product, and in this embodiment, the predetermined action is one of the following actions: "View", "Add to Favorites", and "Purchase". "View" corresponds to the action of accessing (visiting) the sales page and viewing the sales page. "Add to Favorites" corresponds to the action of marking and registering the product sold on the sales page online. "Purchase" corresponds to the action of purchasing the product sold on the sales page. If a "Purchase" action is performed within a specified time after a "View" action, only the "Purchase" action may be registered. Action date and time 304 is information indicating the date and time when the action indicated by action type 303 was performed. The time-series sales page ID list 30 is configured so that newer components appear at the top of the list according to the date and time. Genre ID 305 is information (genre identification information) that identifies the genre of the product sold on the sales page identified by sales page ID 302. Genre ID 305 is used in the second embodiment.

[0028] Referring to Figure 13B, the actions of "browsing," "adding to favorites," and "purchasing" for products sold on the sales page will be explained. Figure 13B shows an example of screen 1310, including sales page 1303, which is displayed when sales page 1302 is selected (activated) and accessed on screen 1300 in Figure 13A. Both sales page 1302 in Figure 13A and sales page 1303 in Figure 13B are sales pages for selling product 1301. Sales pages 1302 and 1303 are examples of sales pages for selling product 1301 and may be composed of other designs or displayed on the screen in different ways. "Browsing" corresponds to the action of accessing sales page 1303 and viewing information about product 1301. "Adding to favorites" corresponds to the action of selecting (activating) the favorites button 1304 on screen 1310 to mark and register product 1301 online. "Purchase" corresponds to the action of selecting (activating) the cart button (a button indicating a shopping cart) 1305 on screen 1310 in order to purchase product 1301, and then proceeding with the purchase procedure. In this embodiment, the action type is assumed to be one of three actions: "Purchase," "Browse," or "Add to Favorites," but it is not limited to these. For example, the access type may include other access types such as searching for or clicking on the product sales page.

[0029] In the information processing device 10, the sales page ID acquisition unit 201 acquires a list of sales page IDs for each user ID from a list of time-series sales page IDs stored in the sales page ID database 240 on the EC site server 11. The product ID list generation unit 202 generates a list of product IDs by converting the sales page IDs included in the list of sales page IDs for each user ID acquired by the sales page ID acquisition unit 201 into product IDs. The recommended product list generation unit 203 determines one or more recommended product IDs for each user ID based on the list of product IDs generated by the product ID list generation unit 202 and generates a list of recommended product IDs. The sales page determination unit 204 determines the sales page of the recommended product (hereinafter also referred to as the recommended sales page) for each user ID based on the list of recommended product IDs generated by the recommended product list generation unit 203. The specific processing by the sales page ID acquisition unit 201, product ID list generation unit 202, recommended product list generation unit 203, and sales page determination unit 204 will be described later.

[0030] [Hardware configuration of information processing equipment] Next, an example of the hardware configuration of the information processing device 10 will be described. Figure 4 is a block diagram showing an example of the hardware configuration of the information processing device 10 according to this embodiment. The information processing device 10 according to this embodiment can be implemented on one or more computers, mobile devices, or any other processing platform. Referring to Figure 4, an example is shown in which the information processing device 10 is implemented in a single computer; however, the information processing device 10 according to this embodiment may be implemented in a computer system including multiple computers. The multiple computers may be connected to each other via a wired or wireless network.

[0031] As shown in Figure 4, the information processing device 10 may include a CPU (Central Processing Unit) 401, a ROM (Read Only Memory) 402, a RAM (Random Access Memory) 403, an HDD (Hard Disk Drive) 404, an input unit 405, a display unit 406, a communication interface 407, and a system bus 408. The information processing device 10 may also include external memory. The CPU 401 comprehensively controls the operation of the information processing device 10 and controls each component (402-407) via the system bus 408, which is a data transmission path.

[0032] ROM402 is a non-volatile memory that stores control programs and other information necessary for the CPU401 to execute processing. This program includes instructions (code) that cause the processing according to the above embodiment to be executed. This program may be stored in non-volatile memory such as HDD404 or SSD (Solid State Drive), or in external memory such as a removable storage medium (not shown). RAM 403 is volatile memory and functions as the main memory, work area, etc., of the CPU 401. In other words, when executing processing, the CPU 401 loads necessary programs, etc., from ROM 402 into RAM 403 and executes these programs, etc., to realize various functional operations. RAM 403 may include the table storage unit 210 and the learning model storage unit 220 shown in Figure 2.

[0033] HDD404 stores various data and information necessary for CPU401 to perform processing using programs, for example. Furthermore, HDD404 also stores various data and information obtained through processing performed by CPU401 using programs, for example. The input unit 405 consists of pointing devices such as a keyboard or mouse. The display unit 406 is comprised of a monitor such as a liquid crystal display (LCD). The display unit 406 may function as a GUI (Graphical User Interface) when configured in combination with the input unit 405.

[0034] Communication I / F 407 is an interface that controls communication between the information processing device 10 and an external device. Communication I / F 407 provides an interface to a network and performs communication with the external device via the network. Various data and parameters are sent and received between the external device and the communication I / F 407. In this embodiment, communication I / F 407 may perform communication via a wired LAN (Local Area Network) or a dedicated line compliant with a communication standard such as Ethernet (registered trademark). However, the network usable in this embodiment is not limited to this and may consist of a wireless network. This wireless network includes wireless PANs (Personal Area Networks) such as Bluetooth (registered trademark), ZigBee (registered trademark), and UWB (Ultra Wide Band). It also includes wireless LANs (Local Area Networks) such as Wi-Fi (Wireless Fidelity) (registered trademark) and wireless MANs (Metropolitan Area Networks) such as WiMAX (registered trademark). Furthermore, it includes wireless WANs (Wide Area Networks) such as 4G and 5G. Furthermore, the network only needs to connect each device in a way that allows it to communicate with one another, and the communication standards, scale, and configuration are not limited to those described above.

[0035] At least some of the functions of the information processing device 10 shown in Figure 2 can be realized by the CPU 401 executing a program. However, at least some of the functions of the information processing device 10 shown in Figure 2 may be operated as dedicated hardware. In this case, the dedicated hardware operates based on the control of the CPU 401.

[0036] The hardware configuration of the EC site server 11 is the same as that shown in Figure 4. Here, RAM 403 may include the sales page ID database 240 and the evaluation index database 250 shown in Figure 2.

[0037] [Process for determining the recommended sales page] Next, the recommended sales page determination process performed by the information processing device 10 according to this embodiment will be specifically described. Figure 5 is a flowchart of the process performed by the information processing device 10 according to this embodiment. The process shown in Figure 5 can be performed by the CPU 401 executing a control program stored in the information processing device 10.

[0038] In S51, the sales page ID acquisition unit 201 acquires a list of sales page IDs for each user ID from the list of time-series sales page IDs collected by the EC site server 11 and stored in the sales page ID database 240. The list of sales page IDs for each user ID corresponds to a list of sales page IDs that identify one or more sales pages associated with a user identified by a user ID. To distinguish the list of sales page IDs for each user ID acquired by the sales page ID acquisition unit 201 from the time-series sales page IDs stored in the sales page ID database 240, it is also referred to as the list of sales page IDs for each user ID. Figure 6 shows an example of the list of sales page IDs for each user 60 acquired by the sales page ID acquisition unit 201. The list of sales page IDs for each user 60 is a list generated by sorting by user ID based on the list of sales page IDs 30 shown in Figure 3. That is, the list of sales page IDs 60 is configured to include information on the sales page ID 302, action type 303, and action date and time 304 for each user ID 301.

[0039] The list 60 of user-specific sales page IDs is a list composed of sales page IDs from the list 30 of sales page IDs within a predetermined period prior to a predetermined timing. This predetermined timing may be the timing when the sales page ID acquisition unit 201 accesses the EC site server 11 to acquire the time-series list of sales page IDs, or a timing arbitrarily set by the sales page ID acquisition unit 201. Alternatively, the list of user-specific sales page IDs may be a list containing sales page IDs corresponding to a predetermined number of actions for each user. That is, the sales page ID acquisition unit 201 may generate and acquire a list of user-specific sales page IDs so that each user contains a predetermined number of sales page IDs corresponding to a predetermined number of actions. In this case, the same number of sales page IDs will be listed for each user ID. Note that although the list 60 of user-specific sales page IDs is sorted by user ID, the list of user-specific sales page IDs may be generated without sorting.

[0040] Next, in S52, the product ID list generation unit 202 converts the sales page IDs included in the sales page ID list obtained by the sales page ID acquisition unit 201 into product IDs and generates a product ID list. In this embodiment, the product ID list generation unit 202 converts the sales page IDs included in the sales page ID list into product IDs using the product conversion table 211 stored in the table storage unit 210. The product conversion table 211 is a table that associates product IDs of products sold by the EC mall with sales page IDs that identify one or more sales pages on which those products are sold.

[0041] In e-commerce malls, the same product may be sold on different sales pages. Therefore, in the product conversion table 211, one product ID may be associated with different sales page IDs. When different sales page IDs are associated with one product ID, the product ID list generation unit 202 converts those different sales page IDs to the same product ID. Figure 13C shows an example of screen 1320 where the same product is sold on different sales pages. In screen 1320, sales page 1306 and sales page 1307 are sales pages that sell the same product 1308. In such a case, the product ID list generation unit 202 converts the sales page IDs of sales page 1306 and sales page 1307 to the product ID of product 1308, respectively.

[0042] Figure 7 shows an example of a list of product IDs for each user ID, converted by the product ID list generation unit 202 from the list of user-specific sales page IDs 60 shown in Figure 6. The product ID list 70 is configured to include product ID 701 for each user ID 301. In the list of user-specific sales page IDs 60, it is assumed that the sales page IDs 302 = "abc121", "bcd942", "bcd125", and "kyr580" for user ID 301 = UID_1 correspond to product IDs = "ABC", "BCD", "BCD", and "KYR", respectively, according to the product conversion table 211. In such a case, the product ID list generation unit 202 lists product IDs 701 = "ABC", "BCD", "BCD", and "KYR" for user ID 301 = UID_1. Here, sales page IDs = "bcd942" and "bcd125" correspond to one product ID = "BCD", but "BCD" is listed for each sales page ID.

[0043] In this embodiment, the product ID list generation unit 202 converted the sales page ID to a product ID by querying the product conversion table 211, but other means may be used to perform this conversion process. For example, the product ID list generation unit 202 may perform this conversion process using a trained machine learning model.

[0044] In S53, the recommended product list generation unit 203 determines the product IDs (recommended product IDs) to recommend for each user ID based on the list of product IDs generated by the product ID list generation unit 202, and generates a list of recommended product IDs. In this embodiment, the recommended product list generation unit 203 inputs a list of product IDs of products for which the user of the user ID has previously taken action (information indicating the list) into the feature vector extraction model 221, and obtains a vector representation of the user of that user ID (hereinafter referred to as the user vector representation). The recommended product list generation unit 203 then embeds the obtained user vector representation into a common vector space. The vector space contains vector representations of product IDs sold on the e-commerce site. The recommended product list generation unit 203 selects (extracts) product IDs with a high similarity to the obtained user vector representation in the vector space. For example, cosine similarity is used as the similarity. Cosine similarity is a measure that represents the similarity between two vectors in a common vector space. The recommended product list generation unit 203 can determine that the greater the cosine value (-1 to +1) of the angle between the user vector representation and the product ID vector representation, the higher the similarity. The recommended product list generation unit 203 calculates the cosine similarity between the acquired user vector representation and the vector representation of an arbitrary product ID in the vector space, and determines a certain number of product IDs with high cosine similarity (for example, above a predetermined threshold) to be included in the recommended product ID list.

[0045] Referring to Figure 7, for example, the recommended product list generation unit 203 inputs a list of product IDs = {ABC, BCD, KYR} for the user with user ID = UID_1 into the feature vector extraction model 221. The feature vector extraction model 221 extracts and outputs the user vector representation of the user with user ID = UID_1 from the input list of product IDs. In other words, the recommended product list generation unit 203 converts the list of product IDs into a user vector representation using the feature vector extraction model 221. Subsequently, the recommended product list generation unit 203 determines the product IDs corresponding to vector representations with high cosine similarity (for example, higher than a predetermined threshold) with the user vector representation in the aforementioned vector space as recommended product IDs. The recommended product list generation unit 203 performs this process for each user ID and generates a list of recommended product IDs for each user ID.

[0046] Figure 8 shows an example of a list of recommended product IDs 80 for each user ID generated by this process. The list of recommended product IDs 80 is structured so that each user ID 301 includes recommended product ID 801. For example, in the list of recommended product IDs 800 for user ID=UID_1, three recommended product IDs are listed: "ABE", "BCP", and "KYQ".

[0047] In S54, the sales page determination unit 204 determines the sales page (recommended sales page) for each of the one or more products recommended to each user, based on the recommended product IDs included in the recommended product list generated by the recommended product list generation unit 203. The sales page determination unit 204 may determine multiple recommended sales pages for each of the one or more products recommended to each user, but in this embodiment, it determines a unique (i.e., one) recommended sales page. First, the sales page determination unit 204 converts the one or more recommended product IDs included in the recommended product list into one or more sales page IDs by querying the product conversion table 211. That is, the sales page determination unit 204 uses the product conversion table 211, which is configured to convert sales page IDs into product IDs, to convert recommended product IDs into sales pages. The sales page determination unit 204 generates a list of recommended sales page IDs that include the one or more converted sales page IDs.

[0048] Figure 9 shows an example of a list 90 of recommended sales page IDs corresponding to each recommended product ID for each user ID, generated based on the list 80 of recommended product IDs shown in Figure 8. The list 90 of recommended sales page IDs is configured to include a recommended product ID 801, a sales page ID 901, and a recommended sales page ID 902 for each user ID 301. The sales page determination unit 204 identifies one or more sales page IDs (candidates for recommended sales page IDs) for each recommended product ID and determines a unique recommended sales page ID from the identified one or more sales page IDs.

[0049] If there is one sales page ID (a candidate for the recommended sales page ID) for one recommended product ID, that sales page ID is determined to be the recommended sales page ID. For example, in the list of recommended sales page IDs 90, for recommended product ID 801="ABE" for user ID=UID_1, recommended sales page ID 902="abe528" is determined. Also, for recommended product ID 801="BCP" for user ID=UID_1, recommended sales page ID 902="bcp182" is determined, and for recommended product ID 801="KYQ", recommended sales page ID 902="kyq490" is determined. In this case, the sales page determination unit 204 determines that the sales pages identified by recommended sales page IDs="abe528", "bcp182", and "kyq490" are the recommended sales pages to be recommended (presented) to the user identified by user ID=UID_1.

[0050] On the other hand, if there are multiple sales page IDs for a single recommended product ID, one sales page ID selected from those multiple sales page IDs is determined as the recommended sales page ID. For example, if user ID = UID_2, there are three sales page IDs corresponding to recommended product ID 801 = "CDT". In this way, when multiple sales page IDs correspond to a recommended product ID, the sales page determination unit 204 may determine one recommended sales page ID based on evaluation metrics associated with the sales page, which are collected by the EC site server 11 and stored in the evaluation metric database 250. For example, if CVR for a sales page is used as an evaluation metric, the sales page determination unit 204 can select a sales page ID with a high CVR as the recommended sales page ID. Stores that sell products on sales pages identified by sales page IDs with high CVRs are considered to have a high level of trustworthiness as a place to buy. Therefore, determining the recommended sales page ID based on CVR can lead to improved usability.

[0051] Furthermore, if multiple sales page IDs exist for a single recommended product ID, the sales page determination unit 204 may determine the recommended sales page ID based on evaluation metrics other than CVR. For example, the sales page determination unit 204 may determine the recommended sales page ID based on an evaluation score for the sales page as an evaluation metric. Alternatively, the sales page determination unit 204 may calculate a recommendation score from the evaluation score and CVR, and determine the recommended sales page ID based on that recommendation score.

[0052] As described above, according to this embodiment, the information processing device 10 converts the sales page information of products associated with each user in the e-commerce mall into product information in the e-commerce mall. That is, the information processing device 10 appropriately associates the sales page information on which each user has taken action with the product information in the e-commerce mall. Then, the information processing device 10 determines recommended products based on the product information and determines a unique sales page for selling those recommended products. This makes it possible to appropriately determine the sales page of the products to recommend to each user.

[0053] <Second Embodiment> The information processing device according to the first embodiment determined the sales page of the product to recommend to each user without considering the product genre (category). The information processing device according to this embodiment estimates one or more genres of interest to each user and determines the recommended sales page limited to those genres. The following describes this embodiment, but the same configuration and features as the first embodiment will be omitted from the description.

[0054] Figure 10 shows an example of the functional configuration of the information processing device 1000 according to this embodiment. Compared to the information processing device 10 according to the first embodiment described with reference to Figure 2, the information processing device 1000 has an additional genre determination unit 205 and a target genre database 260. Furthermore, the learning model storage unit 220 has an MF (Matrix Factorization) based genre prediction model 222 and an NLP (Natural Language Processing (NLP) based genre prediction model 223 added. Although not shown in Figure 10, the information processing device 1000 is connected to the EC site server 11 via a network 13, similar to Figure 2.

[0055] The target genre database 260 stores information about multiple target genres (hereinafter referred to as target genre information) that have been predetermined based on specified criteria. The target genre information stored in the target genre database 260 is generated by a processing unit (not shown) in the information processing device 1000 or by an external device and is updated as needed. The target genre information may be target genre features that represent the characteristics of each of the multiple target genres, or target genre IDs that identify each of the multiple target genres.

[0056] The MF-based prediction model 222 is a model that decomposes an evaluation value matrix consisting of m (rows) × n (columns) (where m and n are integers greater than or equal to 2) into two matrices by dimensionality reduction through collaborative filtering. In this embodiment, the MF-based prediction model 222 is configured to decompose an evaluation value matrix consisting of m user IDs and n genre IDs into a matrix representing user features and a matrix representing genre features. The NLP-based prediction model 223 is a natural language processing model that converts words into vector representations, such as Word2Vec. In this embodiment, the NLP-based prediction model 223 is configured to convert user IDs and genre IDs into user features and genre features. The MF-based prediction model 222 and the NLP-based prediction model 223 are pre-trained models and can be trained by a learning unit (not shown) in the information processing device 10.

[0057] The process performed by the genre determination unit 205 will be explained with reference to Figures 11 and 12. In this embodiment, the genre determination unit 205 determines the genre IDs (top 4 genre IDs) of the top 4 genres of interest to each user. Figure 11 is a flowchart of the genre determination process performed by the genre determination unit 205 according to this embodiment. Figure 12 is a conceptual diagram showing the data flow for determining the top 4 genre IDs. In this embodiment, the process by which the genre determination unit 205 determines the top 4 genre IDs will be explained, but the number of top genre IDs to be determined is not limited to 4.

[0058] In S111, the genre determination unit 205 obtains a list of time-series sales page IDs stored in the sales page ID database 240 of the EC site server 11 (see Figure 3). Subsequently, in S112, the genre determination unit 205 obtains a user ID and a genre ID (see Figure 3) from the list of sales page IDs obtained in S111. As mentioned above, the user ID is associated with the user attributes of the user identified by that user ID. The genre ID, as shown in Figure 3, is an ID that identifies the genre of products sold on the sales page identified by the corresponding sales page ID 302. In Figure 12, the user ID and genre ID obtained by the genre determination unit 205 are represented as user ID 1200 and genre ID 1201, respectively. In Figure 12, user ID 1200 and genre ID 1201 are shown, but the genre determination unit 205 obtains multiple user IDs and multiple genre IDs by sequentially performing this acquisition process.

[0059] In S113, the genre determination unit 205 inputs the user ID 1200 and multiple genre IDs 1201 into a trained genre prediction model to obtain user features 1202 that represent the user's interests and genre features 1203 that represent the characteristics of the genre. The genre prediction model used here is either an MF-based prediction model 222 or an NLP-based prediction model 223. User features 1202 and genre features 1203 can be associated with user ID 1200 and genre ID 1201, respectively.

[0060] When using the MF-based prediction model 222, the genre determination unit 205 first generates an evaluation value matrix consisting of m user IDs and n genre IDs as input data. In the example in Figure 3, there are 3 user IDs (UID_1 to UID_3) and 5 genre IDs (g_1 to g_5), so a 3x5 evaluation value matrix is ​​generated. The values ​​of the elements in the evaluation value matrix can be set by referring to the list of time-series sales page IDs obtained in S111. For example, the genre determination unit 205 refers to the list of time-series sales page IDs obtained in S111 and sets a predetermined value for the genre ID corresponding to each user ID, and sets zero (null value) for genre IDs that do not correspond to each user ID. Referring to Figure 3, the genre determination unit 205 can set the values ​​of the elements of genre IDs = g_1, g_3, and g_4 in the column where user ID = UID_1 to predetermined values, and the values ​​of the elements of genre IDs = g_2 and g_5 to zero. Furthermore, different values ​​may be set for the genre ID corresponding to each user ID, depending on the action type 303 in Figure 3. For example, different values ​​(for example, weight 702 as shown in Figure 15 later) may be set for "Purchase," "Add to Favorites," and "Browse."

[0061] Next, the genre determination unit 205 inputs the generated evaluation value matrix to the MF-based prediction model 222. The MF-based prediction model 222 reduces the dimension of the input evaluation value matrix and outputs two matrices, namely a matrix representing user characteristics and a matrix representing genre characteristics. These user characteristic matrices and genre characteristic matrices can be divided into user characteristics 1202 for each user ID and genre characteristics 1203 for each genre ID. User characteristics 1202 and genre characteristics 1203 are vector representations embedded in a common vector space, corresponding to user embeddings and genre embeddings, respectively.

[0062] On the other hand, when using the NLP-based prediction model 223, the genre determination unit 205 inputs the user ID 1200 and genre ID 1201 to the NLP-based prediction model 223. The NLP-based prediction model 223 converts the user ID and genre ID into vector representations and outputs them as user features and genre features. These user features and genre features are vector representations embedded in a common vector space, corresponding to user embeddings and genre embeddings, respectively.

[0063] In S114, the genre determination unit 205 determines the target genre feature 1204 based on the genre feature 1203 and the target genre information stored in the target genre database 260. In this example, in order to ultimately determine the top 4 genre IDs, target genre information for 5 or more target genres, which is more than the number of top genre IDs, is used. The genre determination unit 205 filters (selects) the genre feature 1203 based on the target genre information and determines the target genre feature 1204. For example, if the target genre information consists of 5 target genre IDs, the genre determination unit 205 determines the genre feature 1203 associated with those 5 target genre IDs as the target genre feature 1204.

[0064] In S115, the genre determination unit 205 determines the top four genre IDs 1205 based on the user characteristics 1202 and the target genre characteristics 1204. The genre determination unit 205 determines the top four genre IDs 1205 according to the similarity between the user characteristics 1202 and the target genre characteristics 1203. For example, cosine similarity is used as this similarity. As mentioned above, cosine similarity is a measure that represents the similarity between two vectors in a common vector space. The genre determination unit 205 can determine that the greater the cosine value (-1 to +1) of the angle between the two vectors, user characteristics 1202 and target genre characteristics 1204, the higher the similarity.

[0065] The top four genre IDs 1205 for each user, determined by the genre determination unit 205, are used to determine the sales pages. For example, the top four genre IDs 1205 may be transmitted to the sales page ID acquisition unit 201. In this case, when the sales page ID acquisition unit 201 obtains a list of sales page IDs for each user as shown in Figure 6, it may exclude genre IDs other than the top four genre IDs. Alternatively, the top four genre IDs 1205 may be transmitted to the sales page determination unit 204. In this case, when the sales page determination unit 204 generates a list of sales page IDs as shown in Figure 9, it may exclude genre IDs other than the top four genre IDs 1205. This determines the recommended sales pages for each user based on the genre IDs included in the top four genre IDs 1205.

[0066] Thus, according to this embodiment, a recommended sales page for products is determined for one or more genres that each user is presumed to be of greater interest to. This makes it possible to appropriately determine the recommended sales page for products recommended to each user, limiting it to one or more genres that align with each user's interests.

[0067] <Third Embodiment> In the above embodiment, the information processing device determined the sales page to recommend to each user based on information collected in response to predetermined actions taken by multiple users on sales pages displayed on the e-commerce mall. In this embodiment, the process of determining the sales page to be presented as default to a user who is accessing (visiting) the e-commerce mall for the first time (hereinafter referred to as a new user) will be described. Since the process according to this embodiment can be performed by any of the information processing devices in the above embodiments, the explanation will be given with reference to the information processing device 10 shown in Figure 2, which was described in the first embodiment.

[0068] The sales page ID acquisition unit 201 acquires a list of time-series sales page IDs collected by the EC site server 11 and stored in the sales page ID database 240. In this embodiment, the list of time-series sales page IDs acquired by the EC site server 11 is not sorted by user, but rather acquired over a predetermined period (for example, from the time of acquisition to a predetermined time prior). An example of the acquired list of sales page IDs is shown in Figure 3. The sales page ID acquisition unit 201 may acquire the list of time-series sales page IDs at predetermined intervals, or it may acquire it when a new user accesses the EC mall.

[0069] Next, the product ID list generation unit 202 generates a list of product IDs from the list of time-series sales page IDs obtained by the sales page ID acquisition unit 201. The procedure for generating the product ID list is as described in the first embodiment and can be performed using the product conversion table 211. Through this process, a list of product IDs is generated that identifies products corresponding to sales pages on which multiple users have taken actions within a predetermined period.

[0070] The sales page determination unit 204 determines the recommended sales pages for one or more products to recommend to the new user, based on the product IDs included in the list of product IDs generated by the product ID list generation unit 202. For example, the sales page determination unit 204 converts the product IDs included in the list of product IDs into one or more sales page IDs using the product conversion table 211, and generates a list of recommended sales page IDs for the new user. Then, the sales page determination unit 204 determines the sales pages identified by the recommended sales page IDs included in the list of recommended sales page IDs as the sales pages to recommend (present) to the new user.

[0071] If the sales page ID acquisition unit 201 acquires a time-series list of sales page IDs at predetermined intervals, the sales page determination unit 204 sequentially generates a list of recommended sales page IDs. The sales page determination unit 204 can then determine which sales page to recommend to the new user based on the list of recommended sales page IDs generated at a time close to when the new user accessed the e-commerce mall. Furthermore, if the sales page ID acquisition unit 201 acquires a time-series list of sales page IDs at the time the new user accessed the e-commerce mall, the sales page determination unit 204 generates a list of recommended sales page IDs corresponding to that time. The sales page determination unit 204 can then determine which sales page to recommend to the new user based on this list of recommended sales page IDs.

[0072] The sales page determination unit 204 may identify a user as a new user who is not included in the browsing history information of the EC mall obtained by the EC site server 11. Alternatively, the sales page determination unit 204 may identify a new user as a new user who is not limited to a user who is accessing the EC mall for the first time, but is not included in the list of time-series sales page IDs obtained by the sales page ID acquisition unit 201.

[0073] The list of time-series sales page IDs obtained by the sales page ID acquisition unit 201 is not limited to a list of time-series sales page IDs obtained by the EC site server 11 within a predetermined period. For example, the sales page ID acquisition unit 201 may acquire a list of time-series sales page IDs limited to a predetermined number of times for one or more action types. Specifically, the sales page ID acquisition unit 201 may limit the acquisition to the "purchase" action and acquire a list of time-series sales page IDs associated with a predetermined number of "purchase" actions from the EC site server 11. Alternatively, the sales page ID acquisition unit 201 may generate a list of time-series sales page IDs obtained for one or more users with user attributes similar to the new user from the list of time-series sales page IDs obtained by the EC site server 11 and output it to the product ID list generation unit 202.

[0074] Thus, according to this embodiment, it is possible to present new users who are accessing the e-commerce mall for the first time with recommended sales pages based on sales pages associated with the action history of other users collected in the past. As a result, new users can view sales pages of products that have been purchased more frequently on the e-commerce mall, which may increase their purchase intent.

[0075] <Fourth Embodiment> In the first embodiment, the recommended product list generation unit 203 generated a list of recommended product IDs using the feature vector extraction model 221 stored in the learning model memory unit 220. However, in this embodiment, the recommended product list generation unit 203 generates this list using a rule-based method. Specifically, the recommended product list generation unit 203 generates a list of recommended product IDs using the recommended product conversion table 212 described below. The following describes this embodiment, but the same configurations and features as in the first embodiment will not be described. It is also possible to apply the second and third embodiments described above to this embodiment.

[0076] Figure 14 shows an example of the functional configuration of the information processing device 1400 according to this embodiment. Compared with the information processing device 10 according to the first embodiment described with reference to Figure 2, the information processing device 1400 has a table storage unit 210 which includes a recommended product conversion table 212. The recommended product conversion table 212 is a table that associates product IDs with recommended product IDs (recommended product identification information) that identify one or more products recommended based on the product identified by the product ID. The recommended product conversion table 212 associates one or more recommended product IDs with product IDs based on past performance. For example, in an e-commerce mall, the recommended product conversion table 212 associates product IDs of products purchased by user groups with similar user attributes with product IDs (recommended product IDs) of one or more other products purchased by users belonging to that group at the same time as or after the purchase of the product in question. If there are many such other products, the product IDs of a predetermined number of products that have a high purchase rate in that user group (i.e., purchased by many users in the user group) may be listed as recommended product IDs. The product conversion table 211 and the recommended product conversion table 212 are generated by a processing unit (not shown) in the information processing device 10 or by an external device and are updated as needed. The information processing device 1400 may also be configured to perform the processing described in the first embodiment simultaneously. In this case, the information processing device 1400 may determine the sales page for one or more recommended product IDs determined by both processes.

[0077] The processing performed by the information processing device 10 according to this embodiment will be described with reference to Figure 5. In Figure 5, the processing in S51 and S52 is as described in the first embodiment. In S53, the recommended product list generation unit 203 generates a recommended product list based on the recommended product conversion table 212. For example, the recommended product list generation unit 203 queries the recommended product conversion table 212 for each product ID included in the list of product IDs 70 shown in Figure 7 to determine the recommended product ID corresponding to each product ID and generates a list of recommended product IDs.

[0078] As an optional process, in S52, if the product ID list generation unit 202 assigns a weight to each product ID indicating the user's level of interest according to the action type, then in S53, the recommended product list generation unit 203 may generate a list of recommended product IDs based on that weight. For example, the "purchase" action for a product is an action that actually acquires the product, and can be said to be an action that indicates a higher level of user interest than the "view" and "add to favorites" actions. Also, the "add to favorites" action for a product is an action that makes it easier to access the sales page of the product again, and can be said to be an action that indicates a higher level of user interest than the "view" action. In this way, a weight corresponding to the user's level of interest can be associated with each product ID.

[0079] Figure 15 shows an example of list 1500, which adds weights 702 according to the action type to the list 70 of product IDs for each user shown in Figure 7. In the example in Figure 15, weights of 1.0 for "Purchase," 0.3 for "Favorites," and 0.2 for "Browse" are assigned to the corresponding product IDs according to the user's level of interest. Note that different weights may be assigned even for the same action type, depending on the action date and time 304 in the list 60 of sales page IDs for each user that corresponds to the list 70 of product IDs. For example, a "Purchase" action performed at a more recent date and time can be said to indicate a higher level of user interest than a "Purchase" action performed at an older date and time. Therefore, a higher weight may be assigned to a "Purchase" action performed at a more recent date and time than to a "Purchase" action performed at an older date and time. For example, the weight of an action performed within a first period, counting back from the date and time the sales page ID list 30 (which forms the basis of sales page ID list 60) was obtained, may be multiplied by a coefficient of 1; the weight of an action performed within a second period, counting back from the first period, may be multiplied by a coefficient of 0.8; and the weight of an action performed before the second period may be multiplied by a coefficient of 0.5. Also, if multiple identical product IDs are listed for the same user, such as product ID 701 = "BCD" in product ID list 70, and each is assigned a weight, the sum of these weights may be assigned to the product ID.

[0080] If weights are assigned according to the action type (weight 702 as shown in Figure 15), the recommended product list generation unit 203 can determine recommended product IDs based on these weights as well. For example, if multiple recommended product IDs correspond to one product ID in the recommended product conversion table 212, the recommended product list generation unit 203 may determine more recommended product IDs for product IDs with higher weights.

[0081] <Variation> In the above embodiment, the sales page ID acquisition unit 201 acquires a time-series list of sales page IDs, and the product ID list generation unit 202 generates a list of product IDs from that list. However, the EC site server 11 may generate the list of product IDs. In this case, the product ID list generation unit 202 may acquire the product ID list generated by the EC site server 11.

[0082] Furthermore, in the fourth embodiment described above, when a weight is assigned according to the action type, the recommended product list generation unit 203 determines the recommended product ID based on that weight as well. However, the weight may be used in other processes. For example, the sales page determination unit 204 may determine the recommended sales pages, and for recommended sales pages with high weights, it may instruct the EC site server 11 to display them in a different manner from other recommended sales pages (for example, to have a more visually appealing effect).

[0083] The effects of the above embodiment and its modifications will be explained with reference to Figures 13A and 13C. In screen 1300 in Figure 13A, multiple products are sold on different sales pages. On the other hand, in screen 1320 in Figure 13C, product 1308 is sold on sales page 1306 and sales page 1307. In such a case, whether a user purchases product 1308 on sales page 1306 or on sales page 1307, the purchase action is associated with product 1308. This makes it possible to accurately aggregate actions for each product, determine appropriate recommended products for the user, and determine the sales page for those recommended products.

[0084] Furthermore, if multiple recommended sales pages are selected for a single product, one (unique) recommended sales page will be determined for that product based on evaluation metrics such as CVR (Conversion Rate). By determining recommended sales pages based on evaluation metrics, sales pages for stores highly rated by multiple users will be selected, potentially improving usability and user purchase intent.

[0085] This embodiment includes the following configuration. [1] Information processing device comprising: an acquisition unit that acquires a list of sales page identification information that identifies each of the sales pages of one or more products associated with each user; a conversion unit that converts the list of sales page identification information into a list of product identification information that identifies products; a generation unit that generates a list of recommended products that includes recommended product identification information that identifies each of the one or more products to be recommended to each user based on the list of product identification information; and a determination unit that determines the sales page of each of the one or more products to be recommended to each user based on one or more of the recommended product identification information included in the list of recommended products.

[0086] [2] The information processing device according to [1], wherein the determination unit determines a unique sales page for each of the one or more products identified by the one or more recommended product identification pieces of information.

[0087] [3] The determination unit identifies one or more sales pages that sell each of the one or more products identified by one or more of the recommended product identification information, and determines the unique page based on the one or more sales pages, as described in [2].

[0088] [4] The information processing device according to [3], wherein if the determination unit identifies one sales page that sells the product identified by the recommended product identification information, it determines the identified sales page as the unique sales page; and if it identifies multiple sales pages that sell the product identified by the recommended product identification information, it determines the unique sales page from among the multiple identified sales pages based on the evaluation indicator associated with the multiple sales pages.

[0089] [5] The information processing device described in [4], wherein the evaluation indicator includes the CVR (conversion rate) for each of the specified sales pages.

[0090] [6] The information processing device according to [4] or [5], wherein the evaluation index includes user ratings for each of the specified sales pages.

[0091] [7] The information processing apparatus according to [1] to [6], further comprising a conversion unit that converts the product identification information included in the list of product identification information into a user vector representation for each user using a machine learning model, wherein the generation unit determines one or more product identification information as the recommended product identification information, corresponding to one or more vector representations on a common vector space in which vector representations of multiple product identification information exist, the cosine similarity with the user vector representation being higher than a predetermined threshold.

[0092] [8] The information processing apparatus according to any one of [1] to [7], further comprising a selection unit for each of the above users to select one or more genres of interest, wherein the acquisition unit acquires a list of sales page identification information for the one or more genres selected for each of the above users.

[0093] [9] The selection unit selects one or more genres for each user using a Matrix Factorization (MF)-based machine learning model, as described in [8].

[0094]

[10] The selection unit selects one or more genres for each user using a natural language processing-based machine learning model, as described in [8].

[0095]

[11] The determination unit further determines one or more products to recommend to users other than each of the users, based on the list of product identification information, and determines their respective sales pages. The information processing device according to any one of [1] to

[10] . [Explanation of Symbols]

[0096] 10: Information processing device, 11: EC site server, 12: User device, 13: Network, 14: User, 201: Sales page ID acquisition unit, 202: Product ID list generation unit, 203: Recommended product list generation unit, 204: Sales page determination unit, 210: Table storage unit, 211: Product conversion table, 212: Recommended product conversion table, 220: Learning model storage unit, 221: Feature vector extraction model, 222: MF (Matrix Factorization) based genre prediction model, 223: Natural Language Processing (NLP) based genre prediction model, 231: EC mall operation unit, 232: Evaluation index derivation unit, 240: Sales page ID database, 250: Evaluation index database, 260: Target genre database

Claims

1. An acquisition unit that acquires a list of sales page identification information that identifies each of the sales pages for one or more products associated with each user in an e-commerce (Electronic Commerce) mall where multiple stores sell the same product and multiple sales pages corresponding to each of the multiple stores are provided for the same product, A first conversion unit converts the aforementioned list of sales page identification information into a list of product identification information that identifies products, A generation unit generates a recommended product list that includes recommended product identification information that identifies one or more products to be recommended to each user, based on the list of product identification information. A decision unit that determines the sales page for each of the one or more products to recommend to each user based on one or more recommended product identification information included in the recommended product list, An information processing device having

2. The information processing apparatus according to claim 1, wherein the determination unit determines a unique sales page for each of the one or more products identified by the one or more recommended product identification pieces of information.

3. The information processing apparatus according to claim 2, wherein the determination unit identifies one or more sales pages that sell each of the one or more products identified by one or more of the recommended product identification information, and determines the unique page based on the identified one or more sales pages.

4. The aforementioned determination unit, If a single sales page selling the product identified by the aforementioned recommended product identification information is identified, that identified sales page is determined to be the aforementioned unique sales page. If multiple sales pages selling the product identified by the aforementioned recommended product identification information are identified, the unique sales page is determined from among the identified multiple sales pages based on the evaluation metrics associated with those multiple sales pages. The information processing apparatus according to claim 3.

5. The information processing apparatus according to claim 4, wherein the evaluation indicator includes the conversion rate (CVR) for each of the specified sales pages.

6. The information processing apparatus according to claim 4 or 5, wherein the evaluation index includes user evaluation scores for each of the specified sales pages.

7. For each of the aforementioned users, the system further includes a second conversion unit that converts the product identification information included in the list of product identification information into a user vector representation using a machine learning model. The information processing apparatus according to claim 1, wherein the generation unit determines one or more product identification information as the recommended product identification information, corresponding to one or more vector representations whose cosine similarity with the user vector representation is higher than a predetermined threshold on a common vector space in which vector representations of multiple product identification information exist.

8. The system further includes a selection section where each user can select one or more genres that they are interested in. The acquisition unit acquires a list of sales page identification information for one or more genres selected for each user. The information processing apparatus according to claim 1.

9. The information processing apparatus according to claim 8, wherein the selection unit selects one or more genres for each user using a Matrix Factorization (MF) based machine learning model.

10. The information processing apparatus according to claim 8, wherein the selection unit selects one or more genres for each user using a natural language processing-based machine learning model.

11. The information processing apparatus according to claim 1, wherein the determination unit further determines one or more products to recommend to users other than each of the aforementioned users, based on the list of product identification information, and determines their respective sales pages.

12. An information processing method performed by an information processing device, The process involves obtaining a list of sales page identification information that identifies each of the sales pages for one or more products associated with each user in an e-commerce (Electronic Commerce) mall where multiple stores sell the same product and multiple sales pages corresponding to each of the multiple stores are provided for the same product, and A conversion process that converts the aforementioned list of sales page identification information into a list of product identification information that identifies products, A generation step of generating a recommended product list that includes recommended product identification information that identifies one or more products to be recommended to each user, based on the list of product identification information; A decision step of determining the sales page for each of the one or more products to be recommended to each user, based on one or more recommended product identification pieces included in the recommended product list, Information processing methods, including those mentioned above.

13. An information processing program for causing a computer to perform information processing, wherein the program causes the computer to perform information processing. An acquisition process to obtain a list of sales page identification information that identifies each of the sales pages for one or more products associated with each user in an e-commerce (Electronic Commerce) mall where multiple stores sell the same product and multiple sales pages corresponding to each of the multiple stores are provided for the same product, A conversion process that converts the aforementioned list of sales page identification information into a list of product identification information that identifies products, A generation process that generates a recommended product list, which includes recommended product identification information that identifies one or more products to be recommended to each user, based on the aforementioned list of product identification information. This process includes a decision process that determines the sales page for each of the one or more products to recommend to each user, based on one or more recommended product identification pieces included in the recommended product list. Information processing program.

Images