Recommendation system, server, recommendation method, and program

The recommendation system addresses the issue of recommending uninteresting items by using user interaction data to update preferences, reducing irrelevant suggestions and improving user engagement through personalized recommendations.

JP7594146B1Active Publication Date: 2024-12-03RAKUTEN GROUP INC
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
JP2024056294
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2024-03-29
Publication Date
2024-12-03
Estimated Expiration
2044-03-29

AI Technical Summary

Technical Problem

Existing recommendation systems often recommend items that users have little interest in, leading to a decrease in user engagement and satisfaction.

Method used

A recommendation system that includes a server and terminal, where the terminal displays a list of recommended items, moves the list based on user interactions, and reports user attention to the server, which identifies viewed and skipped items to update user preferences and generate more relevant future recommendations.

Benefits of technology

The system effectively reduces the recommendation of uninteresting items by identifying and excluding them from future lists, enhancing user engagement and satisfaction by providing more relevant recommendations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007594146000001_ABST
    Figure 0007594146000001_ABST
Patent Text Reader

Abstract

To provide a recommendation system etc. capable of recommending suitable items to a user. [Solution] A recommendation system 100 comprising a server 10 and a terminal 20, in which the server 10 transmits to the terminal 20 a list of items to be recommended to a user using the terminal 20, receives from the terminal a report that a moving operation has been performed in the list to move the range displayed on the screen, receives from the terminal a request for an item page related to an item included in the list, identifies as viewed items items related to the request received from the terminal within a predetermined period after the list related to the report is transmitted to the terminal, and identifies the remaining items after removing the identified viewed items from the list related to the report as skipped items skipped by the user related to the report.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a recommendation system, a server, a recommendation method, and a program. [Background technology]

[0002] 2. Description of the Related Art In a store or the like established on the Internet, a technique has been proposed for displaying a plurality of products related to a product in which a user has shown interest in a recommended product section (for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2008-282098 A Summary of the Invention [Problem to be solved by the invention]

[0004] When recommending items such as products to a user, it is desirable to reduce the possibility that an item that is expected to have little interest to the user will be brought to the user's attention.

[0005] The present invention has been made in consideration of the above-mentioned circumstances, and has an object to provide a recommendation system etc. that can appropriately recommend items to a user. [Means for solving the problem]

[0006] In order to achieve the above object, the recommendation system of the present invention comprises: A recommendation system including a server and a terminal, The terminal includes: receiving from the server a list of items recommended for a user of the terminal; Displaying a portion of the received list on a screen; When a move operation is performed on the list, the range is moved so that another part of the list is displayed on the screen; When a selection operation is performed to select an item included in the list, a request for an item page related to the selected item is transmitted to the server; receiving a response from the server in response to the request; displaying on the screen an item page specified in the received response; When the move operation is performed, a report is sent to the server to the effect that the user has paid attention to the list; The server, receiving said report; Identifying, as viewed items, the items related to the request received from the terminal within a predetermined period after the list related to the report is transmitted to the terminal; The remaining items from the list related to the report after removing the identified viewed items are identified as skipped items skipped by the user related to the report. Effect of the Invention

[0007] According to the present invention, items can be appropriately recommended to a user. [Brief description of the drawings]

[0008] [Figure 1] FIG. 2 is a functional block diagram of a recommendation system and a server according to the present embodiment. [Diagram 2] FIG. 4 is a diagram illustrating an example of user information. [Diagram 3] FIG. 2 is a diagram illustrating an example of a hardware configuration of an information processing device that constitutes the recommendation system according to the present embodiment. [Figure 4] 13 is a flowchart showing an example of a recommendation list providing process. [Diagram 5] 13 is a flowchart illustrating an example of a recommendation list generating process. [Figure 6] 11A and 11B are diagrams showing examples of display of item information and a recommendation list. [Figure 7] FIG. 13 is a diagram showing an example of display of detailed information of an item. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] A recommendation system 100 and a server 10 according to an embodiment of the present invention will be described below with reference to the drawings. Note that the same or corresponding parts in the drawings are given the same reference numerals.

[0010] 1 is a functional block diagram showing the functional configuration of a recommendation system 100 and a server 10 according to the present embodiment. The recommendation system 100 includes a server 10 and a terminal 20. The server 10 and the terminal 20 are connected via a communication network such as the Internet or a mobile communication network, and transmit and receive information via the communication network.

[0011] The recommendation system 100 of this embodiment is a system that recommends items to a user who uses a terminal 20. Specifically, the server 10 generates a recommendation list, which is a list of items to be recommended, based on the user's item viewing history and the like, and provides the generated recommendation list to the terminal 20. The server 10 then identifies the viewed items that the user has viewed and the skipped items that have not been viewed in the provided recommendation list, updates the user's preference settings based on the identification results, and uses them when generating a recommendation list from the next time onwards. The user of the terminal 20 is, for example, a purchaser of an item or a shopper who is a potential purchaser.

[0012] The server 10 is configured with, for example, a communication-enabled information processing device such as a personal computer (PC) or a workstation. The server 10 may be a dedicated device. Although one server 10 is shown in Fig. 1, for example, multiple servers 10 may be provided for each item to be stored and managed.

[0013] The server 10 is functionally composed of a transmission / reception unit 101, a recommendation list generation unit 102, a viewed item / skip item identification unit 103, an item information DB (Data Base) 104, and a user information DB 105, as shown in FIG.

[0014] The transmitting / receiving unit 101 transmits various types of information to the terminal 20 via the communication network, and receives various types of information from the terminal 20.

[0015] The recommendation list generating unit 102 generates a recommendation list based on the browsing history, purchase history, history of recommended items, history of items skipped during recommendation for each user stored in the user information DB 105, and a recommendation model and preference settings generated in advance based on these histories. The recommendation list generating unit 102 estimates items that the user is interested in based on the user's interests and preferences identified from these history information, the similarity between the browsing request and items, and the like, and generates a recommendation list by extracting multiple items stored in the item information DB based on the estimation result and arranging them in a predetermined recommendation order (recommended order).

[0016] The viewed item / skipped item specification unit 103 specifies the items viewed by the user and the items skipped by the user in the recommendation list provided to the terminal 20, and stores the results in the user information DB 105. The stored information is referred to when the recommendation list generation unit 102 generates a new recommendation list from the next time onwards. This makes it possible to provide the user with a recommendation list including more appropriate items according to the user's viewing or skipping situation. For example, it can be estimated that the items viewed by the user are items in which the user is interested and that the recommendation was appropriate, so that the recommendation ranking is raised in the new recommendation list. In addition, it can be estimated that the skipped items skipped by the user are items in which the user is not interested and that the recommendation was inappropriate, so that it can be prevented from being included in future recommendation lists. In this way, it becomes possible to recommend items appropriate to the user.

[0017] The item information DB 104 stores a plurality of pieces of information relating to a specific item. In response to a request from the terminal 20 to browse a specific item specifying the specific item or a request to browse an item specifying search conditions, the transmitting / receiving unit 101 provides a web page of a list of item information of the specified item or a web page including detailed information on the specific item. In this embodiment, an individual web page for an item including detailed information on a specific item is also referred to as an item page. In this manner, the server 10 also functions as a web server that provides a website whose content is item information.

[0018] Then, the server 10 generates a recommendation list by the recommendation list generating unit 102 in response to a request to view an item, etc. The transmitting / receiving unit 101 provides the recommendation list generated by the recommendation list generating unit 102 to the terminal 20 together with the item information. This makes it possible to provide the user of the terminal 20 with information on items recommended to the user in addition to item information on the specified item, thereby making it possible to provide useful information to the user. Note that items recommended to the user by the recommendation list may also be called recommended items. Note that a recommended item may be an item related to an item requested to be viewed by the user, or may be an item extracted from items that the server 10 can provide (for example, an item not related to the item requested to be viewed).

[0019] Thus, in this embodiment, the server 10 provides the recommendation list in response to a request to view items from the terminal 20. Without being limited to this, the server 10 may provide the recommendation list to the user in response to other triggers, such as access to a specific website, a request to acquire the recommendation list itself with conditions specified, etc. Also, the server 10 may generate a recommendation list (a list of products, etc. recommended to the user) and provide it to the terminal 20 as an advertisement on a website or SNS (Social Networking Service).

[0020] An item may be any information that a user may view. For example, an item may be information about products, services, used cars, delivery services, digital content such as books, comics, music, and videos, accommodations, transportation (trains, buses, airplanes, etc.), travel, tours, restaurants, recipes, real estate, beauty facilities (beauty salons, estheticians, etc.), golf courses, leisure facilities such as campsites and fishing boats, sporting events, etc., or information about the purchase or reservation of such items.

[0021] The user information DB 105 stores user information for each user as shown in Fig. 2. The user information includes a user ID for identifying the user, the user's item browsing history, the user's item purchase history, the user's recommendation history, and the user's skip history of items in the user's recommendation list. The user information may include other information such as login information such as a password, and attribute information such as age and gender.

[0022] The item browsing history is information indicating the viewed items for which the user viewed the item page including the item details. For example, simply displaying an overview of an item included in a search result list or recommendation list (such as a link to an item page including the item's name and thumbnail image) does not determine that the item has been viewed. By selecting a specific item from a search result list or recommendation list and browsing an individual item page corresponding to that item, the item is stored as a viewed item in the browsing history of the user information. Since the fact that a user has viewed an item page indicates that the user has a high interest in that item, the items in which the user has a high interest can be estimated from this browsing history.

[0023] The item purchase history is information indicating items that the user has purchased in the past. For example, when an item is purchased from an item page, the item is stored in the purchase history together with the purchase date and time, etc. When a user purchases an item, it can be inferred that the user has a high interest in that item, and therefore the items in which the user has a high interest can be inferred from this purchase history.

[0024] The recommendation history is information on items included in recommendation lists provided to the user in the past. The skip history is information on skipped items that were included in recommendation lists provided to the user in the past but were skipped by the user without viewing them. It can be inferred that the skipped items included in the skip history are of low interest to the user.

[0025] In addition, preference settings obtained by analyzing the preferences of users based on history information related to items for these users may be stored in the user information DB 105. The preference settings may be information indicating fields that the user prefers or does not prefer, product categories, specific item names, etc.

[0026] In this embodiment, the server 10 is configured to include the item information DB 104 and the user information DB 105. However, at least one of the item information DB 104 and the user information DB 105 may be provided outside the server 10.

[0027] The terminal 20 is, for example, an information processing device having a communication function, such as a smartphone, tablet, or PC used by a user. Although one terminal 20 is shown in FIG. 1, the number of terminals 20 may be arbitrary. The terminal 20 transmits an item viewing request to the server 10 via a communication network based on a user's operation. Then, the terminal 20 receives item information and a recommendation list corresponding to the viewing request, which are transmitted from the server 10 based on the item viewing request. The received item information and recommendation list are displayed on the screen of the terminal 20. This allows the user to view the requested item information and also view the recommendation list, which is a list of items recommended based on the request.

[0028] In addition, in the recommendation system 100 of this embodiment, a part of the recommendation list is displayed on the screen of the terminal 20. When a movement operation such as a scroll operation, a movement cursor operation, or a transition operation to the next page is performed on the recommendation list, the display range is moved so that another part of the list is displayed on the screen. That is, the recommendation list can be displayed as a scroll display, a carousel display, or divided into multiple pages, and the items in the list can be displayed part by part. When a movement operation is performed on the recommendation list, the terminal 20 is configured to send a report to the server that the user has paid attention to the recommendation list.

[0029] Furthermore, when a selection operation is performed to select an item included in the recommendation list, the terminal 20 transmits a request for an item page related to that item to the server 10. The terminal 20 receives an item page corresponding to the request from the server 10, and displays the received item page on the screen. That is, the terminal 20 receives a response corresponding to the request from the server 10, and displays the item page specified in the received response on the screen.

[0030] The transmitting / receiving unit 101 of the server 10 in the recommendation system 100 of this embodiment receives a report from the terminal 20 that the user has paid attention to the recommendation list. Then, the viewing item / skipped item identifying unit 103 of the server 10 identifies the items related to the request received from the terminal 20 within a predetermined period after the recommendation list related to the report is transmitted to the terminal 20 as viewing items, and identifies the remaining items from the recommendation list related to the report after removing the identified viewing items as skipped items skipped by the user related to the report. That is, when the user pays attention to the recommendation list, the server 10 identifies the items whose item pages have been viewed within the predetermined period as viewing items in which the user has shown interest, and identifies the items included in the recommendation list that the user has paid attention to but whose item pages have not been viewed within the predetermined period as skipped items in which the user has not shown interest and skipped. Note that the predetermined period may be, for example, a time sufficient for viewing the items in the recommendation list after the recommendation list is provided.

[0031] It can be determined that the skipped items identified in this way were inappropriately recommended to the user. Therefore, by identifying the skipped items and storing their history, the recommendation system 100 and the server 10 can update the user's preference settings, and can exclude the skipped items or lower their recommendation ranking when generating future recommendation lists. This allows the recommendation system 100 and the server 10 to provide an appropriate recommendation list for the user and recommend appropriate items to the user.

[0032] When identifying skipped items, the display range of the recommendation list on the terminal 20 may be identified, and skipped items may be identified from the displayed items. That is, items in the recommendation list that are not displayed on the terminal 20 due to non-scrolling or the like may not be included in the skipped items. This makes it possible to prevent items that are not seen by the user from being identified as skipped items and being excluded from the recommendation list.

[0033] 3 is a diagram showing an example of a hardware configuration of an information processing device constituting the server 10 and the terminal 20. The server 10 has a processor 11 such as a CPU (Central Processing Unit) or a GPU (Graphical Processing Unit), a storage device 12 such as a memory, an HDD (Hard Disk Drive) and / or an SSD (Solid State Drive), a communication interface 13 for performing wired or wireless communication, an input device 14 for accepting an input operation, and an output device 15 for outputting information. The input device 14 is, for example, a keyboard, a touch panel, a camera, a mouse and / or a microphone. The output device 15 is, for example, a display and / or a speaker.

[0034] The processor 11 of the server 10 reads a program stored in the storage device 12, and thereby operates as the various functional units shown in FIG.

[0035] The storage device 12 of the server 10 functions as an item information DB 104 and stores multiple pieces of information on items to be managed. The storage device 12 also functions as a user information DB 105 and stores user information for each user accessed by the terminal 20. At least a part of the information on users may be stored in the storage device 22 of the terminal 20.

[0036] Similarly, the terminal 20 includes a processor 21, a storage device 22, a communication interface 23, an input device 24, and an output device 25. Note that unnecessary components in the server 10 and the terminal 20 may be omitted as appropriate, and other components may be added.

[0037] The processor 21 of the terminal 20 reads a program stored in the storage device 22 to realize a function for using the recommendation system 100. The function may be realized by a dedicated application or a general-purpose web browser. For example, the processor 21 transmits a request to view an item or a request to obtain an item page to the server 10 in response to a user's operation of selecting an item, and obtains item information and a recommendation list from the server 10. In addition, when the processor 21 detects a movement operation in the user's recommendation list, it moves the display range of the recommendation list and transmits a report to the server 10 that the user has paid attention to the list.

[0038] Next, a description will be given of the operation of the recommendation system 100 and the server 10. Fig. 4 is a flowchart showing an example of a recommendation list providing process executed by the server 10. The recommendation list providing process is executed by the processor 11 of the server 10 reading a program stored in the storage device 12.

[0039] In the recommendation list providing process, the server 10 first determines whether or not a user request to view an item related to the server 10 has been received from the terminal 20 (step S11). The user request to view an item is transmitted in response to, for example, an item viewing operation by the terminal 20. If the request to view an item has not been received (step S11; No), the recommendation list providing process is terminated.

[0040] If an item viewing request has been received (step S11; Yes), the server 10 executes a recommendation list generating process for generating a recommendation list to be provided to the terminal 20 of the user who has made the item viewing request (step S12).

[0041] 5 is a flowchart showing an example of a recommendation list generation process. The recommendation list generation process is executed by the recommendation list generation unit 102 of the server 10. In the recommendation list generation process, first, the recommendation list generation unit 102 acquires the user's browsing history from the user information DB 105 (step S121). The recommendation list generation unit 102 also acquires the user's purchase history from the user information DB 105 (step S122). Then, the recommendation list generation unit 102 acquires the recommendation history for the user from the user information DB 105 (step S123). Furthermore, the recommendation list generation unit 102 acquires the user's skip history from the user information DB 105 (step S124).

[0042] In steps S121 to S124, for example, based on a request to view an item, the user ID of the user of terminal 20 that has transmitted the request is identified, and corresponding history information is obtained from user information DB 105.

[0043] Next, the recommendation list generating unit 102 generates a recommendation list by inputting the history information (browsing history, purchase history, recommendation history, and skip history) acquired in steps S121 to S124 into a recommendation model for generating a recommendation list (step S125).

[0044] The recommendation model for generating a recommendation list is a model that outputs a recommendation list when history information is input, and is created in advance by machine learning. As learning data (training data), statistical data such as browsing history and skip history of each user is used. For example, the training data is a list of items in which items purchased or taken by a specific user are assigned a recommendation level of +1, items skipped by a specific user are assigned a recommendation level of -1, and other items are assigned a recommendation level of 0, and the correct answer data is the list of items. A recommendation model is created by preparing a plurality of such training data and having AI (Artificial Intelligence) learn the data. In addition, each time the browsing history of a user is updated from the user information DB 105, training data may be created based on the updated browsing history, and the training data may be re-learned by the recommendation model. The created recommendation model is available for all users. The recommendation model is incorporated into the server 10 as software.

[0045] Then, the recommendation list generating unit 102 receives the recommendation list output from the recommendation model, and generates a recommendation list in which the items are arranged in the order of recommendation to the user (step S126). After that, the recommendation list generating process ends.

[0046] Thus, in this embodiment, the server 10 estimates the user's tastes, items of interest, etc. based on the user's history information (browsing history, purchase history, recommendation history, and skip history), generates a recommendation list in which items are arranged in the order of recommendation to the user, and provides it to the user. This makes it possible to provide a recommendation list suitable for the user, and to recommend items to the user appropriately.

[0047] In this embodiment, the recommendation list generating unit 102 generates the recommendation list by inputting the history information (browsing history, purchase history, recommendation history, and skip history) related to the user into the recommendation model. The method of generating the recommendation list is not limited to this. For example, the recommendation list generating unit 102 may determine the user's preferences and items of interest, etc., using any algorithm based on the history information (browsing history, purchase history, recommendation history, and skip history) related to the user, select items to be recommended, and generate the recommendation list. In addition, the recommendation list generating unit 102 may generate and update the user's preference settings based on the history information related to the user, and select items to be recommended based on the preference settings. That is, the recommendation list generating unit 102 may generate the recommendation list based on at least the skip history by lowering the recommendation ranking of items included in the skip history, or not recommending items included in the skip history. This makes it possible to prevent skip items that are estimated to have little interest to the user from being repeatedly recommended, and to recommend other items instead, so that a recommendation list suitable for the user can be provided. Also, for example, an item included in the purchase history may be excluded from the recommendation list if it is a product that is unlikely to be purchased again.

[0048] The recommendation list generating unit 102 may also generate a recommendation list by extracting items similar to an item related to a user's item viewing request. A predetermined number of items having the same or similar attribute information (category, manufacturer, condition, size, color, region, price range, etc.) as the item specified in the viewing request are extracted. Specifically, a plurality of other items (e.g., different colors, different manufacturers, etc.) belonging to the same category as the item requested to be viewed are listed. Note that any algorithm may be adopted as the algorithm for extracting similar items.

[0049] The recommendation list generating unit 102 may generate a recommendation list in which the extracted items are arranged in the order of recommendation based on the user's history information (browsing history, purchase history, recommendation history, and skip history). For example, the recommendation list generating unit 102 may increase the recommendation rank of items included in the browsing history or purchase history or items that have been viewed many times, and may lower the recommendation rank of items included in the skip history or items that have been skipped many times, or may exclude them from the recommendation list. This allows a recommendation list suitable for the user to be generated.

[0050] In addition, the recommendation list generation unit 102 may randomly determine the recommendation rank in the recommendation list for items with no difference in recommendation rank, or may determine the recommendation rank based on information about the item itself, such as the item's popularity, how recent the information is, and the number of items in stock, as well as other information, to generate the recommendation list.

[0051] In addition, for example, the recommendation list generation unit 102 may generate a recommendation list by referring to the user's own attributes (age, gender, preferences, etc.) and the product viewing and purchasing trends of other users who have attributes in common with the user's own attributes.

[0052] Upon completing the recommendation list generation process, returning to FIG. 4, the server 10 provides the recommendation list generated in step S12 to the user's terminal 20 together with item information in response to the viewing request (step S13). The item information in response to the viewing request may be an item page including detailed information on the specific item if the viewing request is a viewing request for an item page specifying a specific item, or may be a list of search results for items if the viewing request is a viewing request specifying search conditions for an item. The item information in response to the content of the viewing request may be any item information such as summary information, price information, reviews, etc., and the server 10 may simply read the item information in response to the viewing request from the item information DB 104 and provide it to the terminal 20.

[0053] FIG. 6 is a display example of item information and a recommendation list provided from the server 10 to the terminal 20. FIG. 6 shows an example of a case where a web page including item information 112 and a recommendation list display 113 is displayed in tab 1 of the web browser 110 by a web browser (tab browser) 110 installed in the terminal 20. FIG. 6 shows a web page resulting from, for example, a user accessing an item search site and performing a search operation for an item specifying a search condition. In this case, the web browser 110 displays item information 112 such as a list of search results for items in response to a browsing request based on the item search operation. In addition, a recommendation list is provided together with the item information 112. For example, when the item information 112 is scrolled downward, a recommendation list display 113 including a plurality of recommended items is displayed below the item information 112 as shown in FIG. 6.

[0054] In the recommendation list display 113 shown in FIG. 6, the top three items in the recommendation order, such as items RI1, RI2, and RI3, are displayed as recommended items recommended to the user. In this way, in the display example shown in FIG. 6, items in the recommendation list generated by the server 10 are displayed three by three. For example, an overview of each item is displayed for the items RI1, RI2, and RI3, and the overview is a link to detailed information of each item. Also, a scroll button 114 is included for scrolling the items displayed in the recommendation list display 113. In the recommendation list display 113 in FIG. 6, three items are displayed, but the recommendation list generated by the server 10 includes four or more items. Therefore, when the user operates the scroll button 114, the display range of the recommendation list display 113 moves according to the arrangement order (recommendation order) of the recommendation list, and the items are scrolled one by one. Also, an unnecessary selection button ds is displayed for each item RI1, RI2, and RI3. When the unnecessary selection button ds is operated, for example, the item is deleted from the recommendation list display 113. When an item in the recommendation list display 113 is deleted by operating the unnecessary selection button ds, the recommendation list display 113 may be replenished with the next recommended item in the recommendation order.

[0055] The number of items displayed on the recommendation list display 113, i.e., the display range in which the items in the recommendation list transmitted from the server 10 are displayed at one time on the terminal 20, may be any number. Also, the display position of the recommendation list display 113 on the web page may be any position. That is, it is sufficient that the server 10 can provide the recommendation list in a form that allows the user to view it on the terminal 20.

[0056] In addition, in this embodiment, a portion of the recommendation list is displayed by scrolling in response to an operation of the scroll button 114 on the terminal 20, but the recommendation list may also be displayed by scrolling with a mouse or swiping, as a carousel display, or by dividing the list into multiple pages.

[0057] The terminal 20 may be a personal computer, a smartphone, a tablet, etc. The terminal 20 may display item information and a recommendation list in a dedicated application instead of the general-purpose web browser 110.

[0058] 4, the server 10 updates the user's recommendation history (step S14) by adding the items included in the recommendation list provided to the terminal 20 to the recommendation history of the corresponding user in the user information DB 105. Note that if the item viewing request is a request to view an item page and an item page is provided in response to the request, the user's viewing history may also be updated in response to the user viewing the item page.

[0059] Next, the server 10 starts counting up a timer t for measuring the time since the recommendation list was provided to the terminal 20 (step S15).

[0060] Next, the server 10 judges whether or not a report that an operation has been performed on the recommendation list has been received from the terminal 20 that transmitted the recommendation list (step S16).

[0061] The processor 21 of the terminal 20 that has received the recommendation list displays a partial range of the recommendation list on the screen of the terminal 20 (see FIG. 6, for example). Then, when a move operation is performed on the recommendation list, the processor 21 moves the range so that another part of the recommendation list is displayed on the screen. At this time, in this embodiment, the processor 21 is configured to transmit a report to the server 10 that an operation has been performed on the recommendation list. That is, the processor 21 detects an operation on the recommendation list, and if detected, transmits a report to the server 10. In step S16, the server 10 determines whether or not the report has been received from the terminal 20.

[0062] When an operation is performed on a recommendation list, it can be considered that the user has paid attention to the list, so a report that an operation has been performed on a recommendation list can also be said to be a report that the user has paid attention to the list. In the following, such a report that an operation has been performed on a recommendation list or a report that the user has paid attention to the list may be simply referred to as the above-mentioned report.

[0063] When a report is received that an operation has been performed on the recommendation list (step S16; Yes), the server 10 sets a focused list flag indicating that the list has been focused on by the user to ON (step S17). The focused list flag may be provided in a predetermined area of ​​the storage device 12 of the server 10.

[0064] If no report has been received that an operation has been performed on the recommendation list (step S16; No), after executing the processing of step S17, the server 10 determines whether or not a request to obtain an item page (item details) for a specific item has been received from the terminal 20 that sent the recommendation list (step S18).

[0065] When the request to acquire an item page is received (step S18; Yes), the server 10 reads out an item page corresponding to the request from the item information DB 104, and transmits it to the terminal 20 (step S19).

[0066] As an example, when an item RI3 (summary information of item 3) is selected on the screen shown in FIG. 6, a request to acquire the item page of item 3 is sent from terminal 20 to server 10. Then, the item page of item 3 is sent from server 10 to terminal 20. In this case, for example, as shown in FIG. 7, a new tab 2 opens in front of tab 1, and an item page including detailed information 115 of item 3 is displayed on tab 2. This item page is a response to the acquisition request. The detailed information 115 may include text showing details of item 3, price information, purchase information, reservation information, related information, word-of-mouth, review information, and the like. When the item is a product or service, the detailed information 115 may be used to purchase or reserve the product or service. The content of the detailed information 115 may be arbitrary as long as it shows details of the corresponding item. In addition, when the detailed information tab is scrolled by a scroll operation using a scroll bar or a mouse in the state shown in FIG. 7, the information in the lower row can be viewed. By displaying such an item page on terminal 20, it can be inferred that the user is interested in or concerned about the item (item 3 in this case), is considering purchasing, etc. Furthermore, when a link to an item page included in item information 112 is selected on the screen shown in FIG. 6, for example, when a specific item (item name, item summary, thumbnail, etc.) is selected from a list of item search results, the corresponding item page is also transmitted from server 10 and displayed on terminal 20. Note that the item page may be displayed in the same tab (tab 1 in FIG. 6, etc.) as the web page from which the link originates. Furthermore, a recommendation list may be displayed on the item page.

[0067] As described above, when a move operation is performed on the recommendation list, the processor 21 of the terminal 20 transmits a report to the server 10 that an operation on the recommendation list has been performed. As a result, the server 10 determines that the user has paid attention to the recommendation list, and sets the attention list flag to ON in step S17. When the user does not move the recommendation list displayed on the terminal 20, but selects any item in the first view before scrolling of the recommendation list display 113 shown in FIG. 6, for example, the server 10 receives a request to acquire an item page of the item in the recommendation list before the report that an operation on the recommendation list has been performed. In this way, when a selection operation of an item in the recommendation list is performed without moving the recommendation list displayed on the terminal 20, it is preferable that the processor 21 transmits a report to the server 10 that an operation on the recommendation list has been performed together with a request to acquire an item page. As a result, even if an item is selected in the first view of the recommendation list, the server 10 can determine that the user has paid attention to the recommendation list and set the attention list flag to ON. Then, it can be determined that the user has paid attention to the recommendation list at an appropriate timing. The processor 21 may always transmit to the server 10 a report that an operation has been performed on the recommendation list together with a request to acquire an item page. In this case, the processor 21 can omit the process of determining whether a move operation has been performed on the recommendation list.

[0068] If the server 10 has not received a report that an operation has been performed on the recommendation list when it receives a request to obtain an item page, that is, if the attention list flag is off, it may be determined that the user has paid attention to the recommendation list, and the attention list flag may be set to on. This also makes it possible to determine that the user has paid attention to the recommendation list at an appropriate time.

[0069] Then, the server 10 updates the user's browsing history by adding the item corresponding to the item page provided to the terminal 20 to the browsing history of the corresponding user in the user information DB 105 (step S20).

[0070] If the request to obtain the item page has not been received (step S18; No), or after executing the process of step S20, the server 10 determines whether or not other operation information indicating that the user has performed another operation has been received from the terminal 20 (step S21). If other operation information has been received from the terminal 20 (step S21; Yes), the server 10 executes control (e.g., web page update control, etc.) according to the operation information (step S22).

[0071] In step S22, for example, when operation information is received on an item page or the like indicating that a user has purchased an item, the server 10 updates the user's purchase history by, for example, adding the purchased item to the corresponding user's purchase history in the user information DB 105.

[0072] If no other operation information has been received from the terminal 20 (step S21; No), or after the process of step S22, the server 10 judges whether the count value of the timer t has reached a predetermined period (step S23). The predetermined period may be any period determined in advance, and may be, for example, a period of time sufficient for browsing the items in the recommendation list (for example, the number of items in the recommendation list × the predetermined period).

[0073] If the count value of the timer t has not reached the predetermined period (step S23; No), the process returns to step S16, and the server 10 repeats the process according to the received information from the terminal 20.

[0074] If the count value of the timer t has reached the predetermined period (Step S23; Yes), the server 10 resets the count value of the timer t to 0 (Step S24).

[0075] Then, the server 10 judges whether the attention list flag is on or not (step S25). If the attention list flag is off (step S25; No), the server 10 judges that the user does not pay attention to the transmitted recommendation list, and returns to the process of step S16.

[0076] If the attention list flag is on (step S25; Yes), the server 10 determines that the user is paying attention to the recommendation list sent, and identifies items from the recommendation list provided to the terminal 20 that have already been displayed on the screen of the terminal 20 (step S26).

[0077] In step S26, the server 10 may inquire of the terminal 20 about information on how much of the recommendation list has been displayed on the screen. Alternatively, each time a move operation is performed on the recommendation list in the terminal 20, the report may include information on the amount of the move operation and information specifying the items displayed on the screen of the terminal 20 and be sent to the server 10, and the server 10 may identify the displayed items based on the information. Then, for example, when the server 10 is able to identify that up to the Nth item in the display order (recommended order) in the recommendation list has been displayed, the server 10 may identify the items up to the Nth item as the displayed items, and identify the N+1th and subsequent items as the hidden items. In this way, the items that the user has displayed in the recommendation list can be suitably identified.

[0078] After that, the server 10 identifies the displayed items, excluding the items whose item pages in the recommendation list have been viewed, as skip items for which the user has skipped viewing of the item pages, and adds and stores the skip items to the skip history of the corresponding user in the user information DB 105 (step S27). That is, the server 10 identifies, as skip items skipped by the user, items for which the user has not performed a selection operation for a predetermined period of time and whose item pages have not been viewed, even though the recommendation list has been focused on by the user and the items have been displayed in the list.

[0079] Conversely, the server 10 identifies as viewed items those items in a recommendation list that have been selected by the user and whose item pages have been viewed within a specified period of time in the recommendation list that has attracted the user's attention, by adding these items to the user's viewing history in step S20.

[0080] Thereafter, the server 10 clears the attention list flag to off (step S28), returns to the process of step S18, and continues the information transmission in response to the user's operation, etc. By clearing the attention list flag in step S28, the identification of skipped items in the currently provided recommendation list is terminated.

[0081] In this manner, the recommendation system 100 and the server 10 of this embodiment can determine whether or not a user is paying attention to a recommendation list based on whether or not the user has performed an operation on the recommendation list. If the recommendation system 100 and the server 10 determine that the user is paying attention to the recommendation list, it can be inferred that the user is not interested in the items in the recommendation list that have not been viewed within a predetermined period since the recommendation list was provided to the user, or that the recommendation was inappropriate, and therefore the items are identified as skipped items for which the user has skipped viewing of the item page. The recommendation system 100 and the server 10 then store information on the identified skipped items. This allows the recommendation model and the user's preference settings to be updated.

[0082] The recommendation system 100 and the server 10 can use the updated recommendation model and preference settings to generate a recommendation list that is more suitable for the user, and can recommend items to the user. Specifically, since skipped items are less likely to be recommended thereafter, it is possible to reduce the possibility that items that are expected to have little interest in the user will be seen by the user. Furthermore, since items other than skipped items are relatively more likely to be recommended, it becomes easier to provide a recommendation list that includes items that are expected to have a high interest in the user.

[0083] Furthermore, according to the recommendation system 100 and server 10 of this embodiment, skip items are automatically identified according to the browsing status even if the user does not explicitly skip an item, thereby improving user convenience.

[0084] (Modification) The present invention is not limited to the above-described embodiment, and various modifications and applications are possible. For example, some of the above-described embodiment may be omitted or replaced, or any configuration may be added.

[0085] For example, an unnecessary selection button ds is displayed for each of the items RI1, RI2, and RI3 in the recommendation list display 113 shown in FIG. 6. When the unnecessary selection button ds is operated, the item is selected as unnecessary, and the selected item is hidden or darkened in the recommendation list display 113. When an unnecessary selection operation is performed on the terminal 20, the server 10 may be notified of the item selected as unnecessary. Since an item selected as unnecessary is an item in which the user is not interested, the server 10 may store the item as a skipped item in the skip history. In this way, the skipped item can be stored based on the user's explicit unnecessary selection operation and can be used when generating a recommendation list thereafter, allowing the recommendation list to be generated appropriately.

[0086] In contrast to this, in the above embodiment, since skip items can be estimated based on the user's browsing status of the recommendation list without any explicit operation by the user, the unnecessary selection button ds on the recommendation list display 113 may be omitted.

[0087] In the above embodiment, skipped items are identified from among the items included in the recommendation list that have been displayed on terminal 20, but skipped items may be identified from the items included in the recommendation list depending on whether or not the item page has been viewed within a predetermined period of time, regardless of whether or not the item has been displayed on terminal 20. For example, if a displayed item cannot be identified from the items included in the recommendation list because communication with terminal 20 is not required, all items in the recommendation list may be considered to have been displayed, and skipped items may be identified from all items in the recommendation list.

[0088] Furthermore, the server 10 may refer to the information on the identified skipped items when generating a recommendation list thereafter, and may update the recommendation model and the preference settings of each user in any manner based on the skipped items, for example.

[0089] The server 10 and the terminal 20 can be realized by using a normal computer, not by a dedicated device. For example, the server 10 and the terminal 20 that execute the above-mentioned processes may be configured by installing a program for executing the above-mentioned functions on a computer from a recording medium storing the program. Also, one server 10 may be configured by multiple computers operating in cooperation with each other.

[0090] Furthermore, the method for supplying the program to the computer is arbitrary. For example, the program may be supplied via a communication line, a communication network, a communication system, etc. For example, a non-transitory computer-readable recording medium storing the program for executing the above-mentioned functions may be distributed.

[0091] Furthermore, in the case where an OS (Operating System) provides some of the above-mentioned functions, the functions other than those provided by the OS may be provided by a program.

[0092] The above-described embodiments are intended to facilitate understanding of the present invention, and are not intended to limit the present invention. The flow charts, sequences, elements included in the embodiments, and their arrangements, materials, conditions, shapes, sizes, etc. are not limited to those illustrated, and can be changed as appropriate. In addition, configurations shown in different embodiments can be partially substituted or combined with each other.

[0093] (Invention realized by this embodiment) As described above, the present embodiment realizes the following inventions.

[0094] (Appendix 1) A recommendation system including a server and a terminal, The terminal includes: receiving from the server a list of items recommended for a user of the terminal; Displaying a portion of the received list on a screen; When a move operation is performed on the list, the range is moved so that another part of the list is displayed on the screen; When a selection operation is performed to select an item included in the list, a request for an item page related to the selected item is transmitted to the server; receiving a response from the server in response to the request; displaying on the screen an item page specified in the received response; When the move operation is performed, a report is sent to the server to the effect that the user has paid attention to the list; The server, receiving said report; Identifying, as viewed items, the items related to the request received from the terminal within a predetermined period after the list related to the report is transmitted to the terminal; Identifying remaining items from the list related to the report after removing the identified viewed items as skipped items skipped by the user related to the report. Recommendation system.

[0095] (Appendix 2) When the selection operation is performed, the terminal transmits to the server, together with the request, a report that the user has paid attention to the list. Recommendation system according to appendix 1.

[0096] (Appendix 3) If the report is not received for the list related to the request, the server considers the list related to the request as the list related to the report and identifies the view items and the skip items. 3. The recommendation system of claim 1 or 2.

[0097] (Appendix 4) The server, Based on the report, identify hidden items that are not displayed on the screen among the items included in the list; Among the remaining items, the items that are not the hidden items are designated as the skip items. 4. The recommendation system of claim 1, 2 or 3.

[0098] (Appendix 5) In the report, an item in the list that is to be displayed on the screen as a result of the move operation is specified, and an item in the list that is displayed after the specified item in the display order is determined to be the hidden item. The recommendation system described in Appendix 4.

[0099] (Appendix 6) Transmitting a list of items to be recommended to a user of a terminal to the terminal; receiving, from the terminal, a report indicating that a moving operation for moving a range displayed on the screen in the list has been performed; receiving a request from the terminal for an item page relating to an item included in the list; Identifying, as viewed items, the items related to the request received from the terminal within a predetermined period after the list related to the report is transmitted to the terminal; Identifying remaining items from the list related to the report after removing the identified viewed items as skipped items skipped by the user related to the report. server.

[0100] (Appendix 7) A recommendation method executed by a recommendation system including a server and a terminal, The terminal includes: receiving from the server a list of items recommended for a user of the terminal; Displaying a portion of the received list on a screen; When a move operation is performed on the list, the range is moved so that another part of the list is displayed on the screen; When a selection operation is performed to select an item included in the list, a request for an item page related to the selected item is transmitted to the server; receiving a response from the server in response to the request; displaying on the screen an item page specified in the received response; When the move operation is performed, a report is sent to the server to the effect that the user has paid attention to the list; The server, receiving said report; Identifying, as viewed items, the items related to the request received from the terminal within a predetermined period after the list related to the report is transmitted to the terminal; Identifying remaining items from the list related to the report after removing the identified viewed items as skipped items skipped by the user related to the report. Recommendation method.

[0101] (Appendix 8) A recommendation method executed by a server, comprising: Transmitting a list of items to be recommended to a user of a terminal to the terminal; receiving, from the terminal, a report indicating that a moving operation for moving a range displayed on the screen in the list has been performed; receiving a request from the terminal for an item page relating to an item included in the list; Identifying, as viewed items, the items related to the request received from the terminal within a predetermined period after the list related to the report is transmitted to the terminal; Identifying remaining items from the list related to the report after removing the identified viewed items as skipped items skipped by the user related to the report. Recommendation method.

[0102] (Appendix 9) Computer, Transmitting a list of items to be recommended to a user of a terminal to the terminal; receiving, from the terminal, a report indicating that a moving operation for moving a range displayed on the screen in the list has been performed; receiving a request from the terminal for an item page relating to an item included in the list; Identifying, as viewed items, the items related to the request received from the terminal within a predetermined period after the list related to the report is transmitted to the terminal; Identifying remaining items from the list related to the report after removing the identified viewed items as skipped items skipped by the user related to the report. A program that makes it work like this. [Industrial Applicability]

[0103] According to the present invention, it is possible to provide a recommendation system, a server, a recommendation method, and a program that can appropriately recommend items to a user. [Explanation of symbols]

[0104] 10 Server 20 Terminals 11, 21 processor 12, 22 Storage device 13, 23 Communication Interface 14, 24 Input Devices 15, 25 output devices 100 Recommendation System 101 Transmitter / receiver 102 Recommendation list generation unit 103 View Item / Skip Item Specific Section 104 Item Information DB 105 User Information DB 110 Web Browser 112 Item Information 113 Display recommendation list 114 Scroll button 115 More information RI1, RI2, RI3 items (recommended items) ds Unnecessary selection button

Claims

1. A recommendation system including a server and a terminal, The terminal includes: receiving from the server a list of items recommended for a user of the terminal; Displaying a portion of the received list on a screen; When a move operation is performed on the list, the range is moved so that another part of the list is displayed on the screen; When a selection operation is performed to select an item included in the list, a request for an item page related to the selected item is transmitted to the server; receiving a response from the server in response to the request; displaying on the screen an item page specified in the received response; When the move operation is performed, a report is sent to the server to the effect that the user has paid attention to the list; The server, receiving said report; Identifying, as viewed items, the items related to the request received from the terminal within a predetermined period after the list related to the report is transmitted to the terminal; Identifying remaining items from the list related to the report after removing the identified viewed items as skipped items skipped by the user related to the report. Recommendation system.

2. When the selection operation is performed, the terminal transmits to the server, together with the request, a report that the user has paid attention to the list. The recommendation system of claim 1 .

3. If the report is not received for the list related to the request, the server considers the list related to the request as the list related to the report and identifies the view items and the skip items. The recommendation system of claim 1 .

4. The server, Based on the report, identify hidden items that are not displayed on the screen among the items included in the list; Among the remaining items, the items that are not the hidden items are designated as the skip items. The recommendation system of claim 1 .

5. In the report, an item in the list that is to be displayed on the screen as a result of the move operation is specified, and an item in the list that is displayed after the specified item in the display order is determined to be the hidden item. The recommendation system according to claim 4 .

6. Transmitting a list of items to be recommended to a user of a terminal to the terminal; receiving, from the terminal, a report indicating that a moving operation has been performed to move a range displayed on the screen in the list; receiving a request from the terminal for an item page relating to an item included in the list; Identifying, as viewed items, the items related to the request received from the terminal within a predetermined period after the list related to the report is transmitted to the terminal; Identifying remaining items from the list related to the report after removing the identified viewed items as skipped items skipped by the user related to the report. server.

7. A recommendation method executed by a recommendation system including a server and a terminal, The terminal includes: receiving from the server a list of items recommended for a user of the terminal; Displaying a portion of the received list on a screen; When a move operation is performed on the list, the range is moved so that another part of the list is displayed on the screen; When a selection operation is performed to select an item included in the list, a request for an item page related to the selected item is transmitted to the server; receiving a response from the server in response to the request; displaying on the screen an item page specified in the received response; When the move operation is performed, a report is sent to the server to the effect that the user has paid attention to the list; The server, receiving said report; Identifying, as viewed items, the items related to the request received from the terminal within a predetermined period after the list related to the report is transmitted to the terminal; Identifying remaining items from the list related to the report after removing the identified viewed items as skipped items skipped by the user related to the report. Recommendation method.

8. A recommendation method executed by a server, comprising: Transmitting a list of items to be recommended to a user of a terminal to the terminal; receiving, from the terminal, a report indicating that a moving operation has been performed to move a range displayed on the screen in the list; receiving a request from the terminal for an item page relating to an item included in the list; Identifying, as viewed items, the items related to the request received from the terminal within a predetermined period after the list related to the report is transmitted to the terminal; Identifying remaining items from the list related to the report after removing the identified viewed items as skipped items skipped by the user related to the report. Recommendation method.

9. Computer, Transmitting a list of items to be recommended to a user of a terminal to the terminal; receiving, from the terminal, a report indicating that a moving operation has been performed to move a range displayed on the screen in the list; receiving a request from the terminal for an item page relating to an item included in the list; Identifying, as viewed items, the items related to the request received from the terminal within a predetermined period after the list related to the report is transmitted to the terminal; Identifying remaining items from the list related to the report after removing the identified viewed items as skipped items skipped by the user related to the report. A program that makes it work like this.

Citation Information

Patent Citations

  • Commodity recommendation system

    JP2008282098A

  • Information processing system, information processing method, and information processing program

    JP2019015997A

  • Selectively replacing displayed content items based on user interaction

    US20170147156A1

  • Presentation device, presentation method, non-transitory computer-readable information recording medium, and program

    WO2017098576A1