Item list providing system, item list providing server, item list providing terminal, item list providing method, and item list providing computer program

Abstract

In a project list providing system (100) equipped with a server (10) and a terminal (20), the server (10) and the terminal (20) cooperate to perform the following process: generating a list that arranges a plurality of items in the order recommended to the user; prompting the user with the items included in the generated list according to the order in the list; when the user performs a non-demand filtering operation to specify non-demand items in the self-suggested items, identifying low-interest items in the list that are similar to non-demand items and have not yet been prompted to the user, and reducing the order of low-interest items in the list.

Description

Technical Field

[0001] The present invention relates to an item list providing system, a server, a terminal, an item list providing method, and a program. Prior Art

[0002] There is proposed a technology for displaying a plurality of products related to a product that a user is interested in in a recommended product column in a store opened on the Internet (for example, Patent Document 1). [Prior Technical Literature] [Patent Document]

[0003] Patent Document 1: Japanese Patent Application Publication No. 2008-282098 Summary of the invention

[0004] [Problems to be solved by the invention]

[0005] When recommending items such as merchandise to users, it is desirable to reduce the likelihood that items that the user is not expected to be interested in will be viewed by the user.

[0006] The present invention is completed in view of the above-mentioned circumstances, and its purpose is to provide an item list providing system that can appropriately recommend items to users. [Technical means to solve the problem]

[0007] To achieve the above-mentioned purpose, the project list providing system of the present invention is provided with a server and a terminal, and the server and the terminal cooperate to perform the following processing: generating a list of multiple items in the order of recommendation to the user; Prompt the user with the items included in the generated list according to the order in which they are arranged in the list; When the user performs a non-demand screening operation to specify a non-demand item from the items suggested, identify low-interest items that are similar to the non-demand item and have not yet been suggested to the user from among the items arranged in the list; Lower the order of the above low interest items in the above list.

[0008] The server of the present invention comprises: a generating unit, which generates a list in which a plurality of items are arranged in the order of recommendation to the user; a providing unit, which provides the items included in the generated list to the terminal according to the order in which the items are arranged in the list, and displays the items on the screen of the terminal; A receiving unit, which receives a report from the terminal, the report indicating that a non-demand screening operation of specifying non-demand items from the items displayed on the screen has been performed in the terminal; A specifying section, which specifies similar items that are similar to the non-demand items among the items arranged in the list and are non-displayed items that have not yet been displayed in the screen, i.e., low-interest items; and An update section that lowers the order of the above-mentioned low-interest items in the above-mentioned list.

[0009] Alternatively, the report may further include: display information showing which of the items included in the list is displayed on the screen of the terminal; and The items not displayed in the above-mentioned display information are set as the above-mentioned non-display items.

[0010] Alternatively, items that have not yet been provided to the terminal may be set as the non-display items.

[0011] It may also re-recommend new items that are not similar to the above non-needed items and are not included in the above list; and In the above list, the above new item is added between the order of the items already provided to the above terminal and the order of the above low-interest items.

[0012] The terminal of the present invention has: An acquisition unit, which acquires a list of a plurality of items arranged in a recommended order from a server; A display unit, which displays the above-obtained list in a scrollable manner on the screen; An accepting section accepts a non-demand screening operation of specifying non-demand items from the items arranged in the above list and displayed in the above screen; A specifying section, which specifies similar items that are similar to the non-demand items among the items arranged in the list and are non-displayed items that have not yet been displayed in the screen, i.e., low-interest items; and An update section that lowers the order of the above-mentioned low-interest items in the above-mentioned list.

[0013] Alternatively, by reporting the non-required items to the server, the server may lower the priority of recommending the reported items.

[0014] Alternatively, by reporting the non-required item to the server, the server may identify similar items in the items arranged in the list that are similar to the non-required item.

[0015] Alternatively, a table of similarities between items arranged in the list may be obtained from the server together with the list; and From the above table, the above similarity between each of the above non-display items and the above non-required items is obtained.

[0016] Alternatively, the feature vector of each item arranged in the above-mentioned list may be obtained from the above-mentioned server together with the above-mentioned list; and Based on the feature vector, the similarity between each of the non-display items and the non-required item is calculated.

[0017] Alternatively, the similarity calculated above may be compared with a specified threshold value to identify the similar items, or the items having a specified number or a specified proportion of the similarity calculated above may be identified as the similar items and the low-interest items.

[0018] Alternatively, the server may be configured to recommend new items that are not similar to the non-required items; and The new items are added to the above list in order of being higher than the low interest items.

[0019] The project list providing method of the present invention is a project list providing method in a project list providing system having a server and a terminal, and the server and the terminal cooperate to perform the following processing: generating a list of multiple items in the order of recommendation to the user; Prompt the user with the items included in the generated list in the order in which they are arranged; and When the user performs a non-demand screening operation to specify a non-demand item from the items presented, identify low-interest items that are similar to the non-demand item and have not yet been presented to the user from among the items arranged in the list; Lower the order of the above low interest items in the above list.

[0020] The program of the present invention enables the computer to function as the following mechanism: A generating unit, which generates a list in which a plurality of items are arranged in the order of recommendation to the user; A providing unit, which provides the items included in the generated list to the terminal according to the order in which they are arranged in the list, and displays them on the screen of the terminal; A receiving unit, which receives a report from the terminal, the report indicating that a non-demand screening operation of specifying non-demand items from the items displayed on the screen has been performed in the terminal; A specifying section, which specifies similar items that are similar to the non-demand items among the items arranged in the list and are non-displayed items that have not yet been displayed in the screen, i.e., low-interest items; and An update section that lowers the order of the above-mentioned low-interest items in the above-mentioned list.

[0021] Another program of the present invention enables the computer to function as the following mechanism: An acquisition section, which acquires a list of multiple items arranged in a recommended order; A display unit, which displays the above-obtained list in a scrollable manner on the screen; An accepting section accepts a non-demand screening operation of specifying non-demand items from the items arranged in the above list and displayed in the above screen; A specifying section, which specifies similar items that are similar to the non-demand items among the items arranged in the list and are non-displayed items that have not yet been displayed in the screen, i.e., low-interest items; and An update section that lowers the order of the above-mentioned low-interest items in the above-mentioned list. [Effects of the Invention]

[0022] According to the present invention, items can be appropriately recommended to users. Simple diagram description

[0023] FIG. 1 is a block diagram showing the structure of the system for providing an item list according to the present embodiment. FIG. 2 is a diagram showing an example of the hardware configuration of an information processing device constituting the item list providing system of the present embodiment. FIG. 3 is a flow chart showing an example of the recommendation list prompting process in the first embodiment. FIG. 4 is a flow chart showing an example of the process of generating a recommendation list. FIG. 5 is a diagram showing an example of displaying item information and a recommendation list. 6(A) to (D) are diagrams showing display examples of a recommendation list. FIG. 7 is a flow chart showing an example of the recommendation list providing process in the second embodiment. FIG. 8 is a diagram showing a method for managing a recommendation list in the second embodiment. 9(A) to (F) are diagrams showing an example of updating the recommendation order of the recommendation list in Implementation Form 2. FIG. FIG. 10 is a flow chart showing an example of the recommendation list display processing in the third embodiment. FIG. 11 is a diagram showing a method for managing a recommendation list in implementation form 3. Figures 12(A) to (F) are diagrams showing an example of updating the recommendation order of the recommendation list in implementation form 3. Implementation

[0024] Hereinafter, the item list providing system 100 according to the embodiment of the present invention will be described with reference to the drawings. In addition, the same or corresponding parts in the drawings are marked with the same symbols.

[0025] FIG. 1 is a block diagram showing the structure of an item list providing system 100 of the present embodiment. The item list providing system 100 is a system for providing a list of recommended items (suggestions) to a user, i.e., a recommendation list. The item list providing system 100 is composed of a server 10 and a terminal 20. The server 10 and the terminal 20 are connected via a communication network 30 such as the Internet or a mobile communication network. The server 10 and the terminal 20 transmit and receive information via the communication network 30.

[0026] The server 10 memorizes information related to a plurality of specified items, generates a list (recommended item list) in which the items are arranged in the order of recommendation to the user, i.e., the order of recommendation, and provides it to the terminal 20 via the communication network. For example, the server 10 provides the item information of the specified item in response to a browse request for an item specifying a specific item or a browse request for an item specifying a search condition from the terminal 20. In this way, the server 10 also functions as a web server that provides a website with item information as content. Furthermore, the server 10 provides the item information to the terminal 20 together with a recommendation list in which items similar to the item are arranged in a recommended order, for example. In this way, in addition to the item information of the specified item, the user of the terminal 20 can also be provided with a recommendation list of items recommended based on the item, thereby providing useful information to the user. In addition, there is also a case where the item recommended to the user by the recommendation list is called a recommended item.

[0027] Thus, in this embodiment, the server 10 provides the recommendation list in response to the browsing request of the item from the terminal 20, but the recommendation list may be provided to the user in response to other opportunities such as accessing a specified website, requesting to obtain the recommendation list of specified conditions, etc. In addition, the recommendation list (a list of products recommended to the user) may be generated in the server 10 as an advertisement on a website or SNS (Social Networking Service) and provided to the terminal 20.

[0028] The items can be any information that the user browses. For example, the items can be related to goods, services, used cars, takeout, digital content such as books / comics / music / videos, accommodation facilities, transportation facilities (trains, buses, airplanes, etc.), travel, sightseeing, restaurants, recipes, real estate, beauty facilities (beauty salons / beauty clinics, etc.), golf courses, camping grounds / fishing boats and other leisure facilities, sports activities, etc., or purchase information or reservation information.

[0029] The server 10 is composed of a communication-capable information processing device such as a personal computer (PC) or a workstation. In addition, the server 10 may also be a dedicated device. In FIG. 1 , one server 10 is shown, but for example, a plurality of servers 10 may be provided for each item to be stored and managed.

[0030] The terminal 20 is, for example, an information processing device having a communication function such as a smartphone, tablet computer, or PC used by a user. The terminal 20 sends a browse request for an item to the server 10 via the communication network 30 based on the user's operation. Then, the terminal 20 obtains the item information and the recommendation list corresponding to the browse request sent from the server 10 based on the browse request for the item. The obtained item information is displayed on the screen of the terminal 20. In addition, the obtained recommendation list can be displayed in a scrolling manner on the screen of the terminal 20, and the items in the list can be browsed sequentially one by one. In this way, the user can browse the requested item information and browse the list of items recommended based on the request, that is, the recommendation list. In FIG. 1 , one terminal 20 is shown, but the number of terminals 20 can be arbitrary.

[0031] FIG2 is a diagram showing an example of the hardware configuration of the 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) and a GPU (Graphics Processing Unit), a memory, a storage device 12 such as a HDD (Hard disk drive) and / or an SSD (Solid State Drive), a communication interface 13 for wired or wireless communication, an input device 14 for receiving input operations, 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.

[0032] The memory device 12 of the server 10 stores information of a plurality of managed items. In addition, the information of each user accessed by the terminal 20 (not the information of the required items, the information of the recommended priority order) is stored. At least a part of the information related to the user can also be stored in the memory device 22 of the terminal 20.

[0033] The terminal 20 also has a processor 21, a memory device 22, a communication interface 23, an input device 24, and an output device 25. In addition, the server 10 may appropriately omit unnecessary components of the terminal 20, and may also add other components.

[0034] In addition, in the item list providing system 100 of this embodiment, a non-needed filtering operation of the user specifying a non-needed item from the items included in the recommendation list presented to the user can be accepted. Furthermore, the item list providing system 100 causes the server 10 and the terminal 20 to cooperate to perform a process of specifying a low-interest item that is similar to the specified non-needed item and has not been presented to the user, and lowering the recommendation order of the low-interest item in the recommendation list. In this embodiment, the recommendation list can sequentially present the items included in the list by scrolling, etc., and present the list part by part. Furthermore, by lowering the recommendation order (specifically, the display order of the list) of the low-interest item that is similar to the non-needed item based on the user's non-needed filtering operation and has not been presented to the user to the lower level, and by using scrolling, etc. to put the order presented to the user at the back, the low-interest item is not easily seen by the user. In this way, a better recommendation list corresponding to the user's non-needed filtering operation can be presented.

[0035] (Implementation form 1) Hereinafter, first, an example of a case where the server 10 and the terminal 20 cooperate to manage the recommendation list in the entire item list providing system 100 and lower the recommendation order of the low-interest items in the recommendation list, that is, embodiment 1, will be described. In embodiment 1, the item list providing system 100 presents the recommendation list as a "prompt".

[0036] FIG. 3 is a flowchart showing an example of a recommended list presentation process performed by the item list providing system 100 of Embodiment 1. The recommended list presentation process is performed by the processor 11 of the server 10 and the processor 21 of the terminal 20 in cooperation. Specifically, the recommended list presentation process is performed by the processor 11 reading a program stored in the memory device 12 and the processor 21 reading a program stored in the memory device 22. In addition, in the process of FIG. 3, the process of which the subject is not particularly specified can be performed by at least one of the server 10 and the terminal 20.

[0037] In the process of prompting the recommended list, the item list providing system 100 first determines whether there is a user's browsing request for the item on the server 10 (step S11). The user's browsing request for the item is, for example, a browsing operation of the item by the terminal 20. If there is no user's browsing request for the item (step S11; No), the process of prompting the recommended list ends.

[0038] If there is a user's browsing request for the project (step S11; yes), the project list providing system 100 executes a recommendation list generation process for generating a recommendation list for prompting the user who makes the browsing request for the project (step S12).

[0039] FIG. 4 is a flow chart showing an example of a recommendation list generation process. The recommendation list generation process is executed by the processor 11 of the server 10. In the recommendation list generation process, first, the processor 11 extracts items similar to the items in the user's item browsing request (step S121). In step S121, for example, a specified number of items having the same or similar attribute information (type, manufacturer, state, size, color, region, price range, etc.) as the item specified in the browsing request are extracted. Specifically, a plurality of other items of the same type as the item with the browsing request (for example, different colors, different manufacturers, etc.) are listed. In addition, the algorithm used to extract similar items can also adopt any algorithm.

[0040] Next, the processor 11 obtains the recommendation priority information of the user who makes a browsing request for the item (step S122).

[0041] Next, the processor 11 generates a recommendation list based on the recommendation priority information obtained in step S122, which arranges the plurality of items captured in step S121 in the order of recommendation to the user (step S123). Thereafter, the recommendation list generation process ends.

[0042] The recommendation priority information is information showing the recommendation priority of each user's items, and is, for example, stored in the storage device 12 of the server 10 in correspondence with the user's identification information. In the recommendation list presented to the user, when the user performs a non-needed screening operation, the recommendation priority information is updated in a manner that lowers the recommendation order of the items selected as non-needed items. The recommendation priority information may also be information that stores at least non-needed items that have been subjected to a non-needed screening operation. In addition, for example, when the user performs a browsing operation of a specified item, the recommendation priority information is updated in a manner that raises the priority of the item.

[0043] In step S123, when regenerating the recommendation list, the recommendation priority information is referred to, for example, the items captured in step S121 are arranged in the recommendation list in order of priority. In addition, as long as non-needed items based on the user's past non-needed screening operations are not put into the recommendation list, or the recommendation list is generated with a lower recommendation order, a recommendation list suitable for the user can be generated.

[0044] In addition, the browsing history of the user's items can be memorized together with the recommendation priority information. Furthermore, the browsing history of the items can be referenced to generate a recommendation list.

[0045] Furthermore, for items that have no difference in the recommendation priority order based on the recommendation priority order information, the recommendation order of the recommendation list may be randomly determined, or the recommendation order may be determined based on the item's own information such as the popularity of the item, the newness of the information, the inventory quantity, or other information to generate the recommendation list. Furthermore, when referring to the browsing history of the user's items, the recommendation order of the items that have been browsed in the past and the items that have been browsed many times may be increased.

[0046] Furthermore, for example, in the process of generating a recommendation list, reference may be made to the user's past browsing / purchased merchandise tendencies, the user's own attributes (age, gender, hobbies, etc.), the browsing / purchased merchandise tendencies of other users who have attributes common to the user's own attributes, etc., and a predicted purchase / browsing list may be generated based on, for example, machine learning.

[0047] When the recommendation list generation process is completed, returning to FIG. 3, the item list providing system 100 presents the recommendation list generated in step S12 to the user together with the item information corresponding to the browsing request (step S13). For the item information corresponding to the browsing request, if the browsing request is a browsing request that specifies a specific item, then only the information of the specific item (for example, a product summary, price information, etc.) is sufficient; if the browsing request is a browsing request that specifies the search conditions of the item, then only the search results of the item (equivalent to the list and summary of the items of the search conditions, etc.) are sufficient.

[0048] FIG. 5 is a display example of item information and a recommended list presented by the item list providing system 100. As an example, FIG. 5 shows an example of a situation in which a user accesses an item search website through a web browser 110 installed in a terminal 20 and performs a browsing operation for a specific item, and as a result, a web page containing item information and a recommended list of the specific item is displayed in the web browser 110. As shown in FIG. 5, item information such as an item name 111 and item detailed information 112 corresponding to the item browsing operation (browsing request) is displayed in the web browser 110. In addition, a recommended list 113 is displayed together with the item information. In the recommended list 113 shown in FIG. 5, three items in the recommended order of items RI1, RI2, and RI3 are displayed as recommended items recommended to the user. In this way, in the display example shown in FIG. 5, the items in the recommended list generated by the item list providing system 100 are displayed three by three. For example, the outline of each item is displayed in items RI1, RI2, and RI3, which serves as a link to the detailed information of each item. In addition, a scroll button 114 is displayed for scrolling the items displayed in the recommendation list 113. In the recommendation list 113 of FIG. 5 , the items are displayed three by three, but the recommendation list generated by the item list providing system 100 includes more than four items, and by operating the scroll button 114, the items are scrolled and displayed one by one in sequence according to the order (recommendation order) of the item list.

[0049] Next, the item list providing system 100 determines whether the user performs a non-needed screening operation of specifying non-needed items in the recommended list presented to the user (step S14).

[0050] When the user performs a non-needed filtering operation (step S14; yes), the item list providing system 100 sets the selected non-needed item to be non-displayed in the recommendation list (step S15). This prevents the user from continuing to see items that the user does not need. At this time, the items of the non-needed filtering operation are memorized as non-needed items in the recommendation priority information corresponding to the user (for example, the non-needed items of the non-needed filtering operation are reported from the terminal 20 to the server 10, and the non-needed items are memorized in the recommendation priority information). Therefore, the non-needed item is not easily recommended or is not recommended to the user afterwards.

[0051] On each of the items RI1, RI2, and RI3 shown in FIG5, a non-need selection button ds is displayed. When the non-need selection button ds is operated, a non-need filtering operation is performed on the item, and the selected item is not displayed. For example, FIG6 is an example of display of a recommendation list. For example, as shown in FIG5 and FIG6(A), in a state where three items RI1, RI2, and RI3 in the upper order of recommendation are displayed in the recommendation list 113 as preset display items, when the non-need selection button ds of the item RI2 is selected for operation (non-need filtering operation), as shown in FIG6(B), the item RI2 is not displayed, and the deleted item DI is displayed in the place where the item RI2 is displayed. In addition, a cancel button rs is displayed in the deleted item DI, and when the cancel button rs is operated, the non-need filtering operation is canceled, and the item RI2 is displayed again. In this way, in the case where the non-need selection button ds is operated by mistake, the operation can be canceled. In this case, the subsequent low-interest item specific processing is not performed. In addition, the deleted item DI can also be a display of the item before deletion. For example, against the background of the deleted item DI, the item RI2 before deletion can also be displayed thinner or darker.

[0052] Furthermore, the item list providing system 100 performs low-interest item specific processing, that is, it identifies low-interest items that are similar to non-demand items that are screened by the user and are not prompted to the user from among the items included in the recommendation list (step S16).

[0053] In the specific processing of low-interest items, for example, non-demand items are compared with other items included in the recommendation list that are not prompted to the user, and similar items to the non-demand items included in the recommendation list are specified as low-interest items.

[0054] The method of determining similar items can be, for example, based on the commonality of attribute information (type, manufacturer, state, size, color, region, price range, etc.), or based on a similarity table prepared in advance to classify the similarity of each item. In addition, the feature vector or feature amount of the elements (image data, text data, etc.) of each item can be obtained, and similar items can be determined based on the similarity of the feature vector or feature amount. In other words, similar items can be identified by any method.

[0055] In addition, the items included in the recommendation list may be compared with the non-needed items to obtain similarity, and the items whose similarity is within a predetermined threshold may be selected as similar items (low interest items). In addition, the items whose similarity is a predetermined number or a predetermined ratio of the upper level may be selected as similar items (low interest items).

[0056] Whether the item is not shown in the recommendation list can be determined by obtaining browsing status by scrolling the recommendation list in the terminal 20 or by determining whether the item has been provided to the terminal 20 from the server 10.

[0057] When a low-interest item is identified, the item list providing system 100 lowers the recommendation order of the low-interest item in the recommendation list (step S18). In this way, in the recommendation list, since the recommendation order of the low-interest item that has not yet been prompted to the user is lowered, when the user browses the recommended items in sequence, the possibility of the user seeing items that are expected to be of no interest to the user can be reduced.

[0058] Next, the item list providing system 100 replenishes the recommended items according to the number of low-interest items in the recommendation list and updates the recommendation list (step S19). For example, in the recommendation list, the recommendation order of the low-interest items is reduced to the lowest level, and the new recommended items with the same number as the low-interest items are added to the recommendation list in a higher order than the low-interest items. In other words, the item list providing system 100 adds the newly recommended items to the order between the items that have been prompted and the order of the low-interest items. In this way, the new items corresponding to the number of low-interest items can be added to the recommendation list, and the new items can be recommended in a higher order than the low-interest items. In addition, the method for extracting the supplementary recommended items only needs to use the same algorithm as when the recommendation list is generated. For example, it is sufficient to supplement the recommended items that are not included in the initially generated recommendation list, the items recommended at the next point, and the recommended items that are not equivalent to the low-interest items.

[0059] In addition, the number of recommended items added is not limited to the same as the number of low-interest items, and can be a specified ratio of the number of low-interest items, or can be more or less than the number of low-interest items. In addition, the order of adding new recommended items can be any order.

[0060] After the processing of step S19, or when the user does not perform a non-needed screening operation (step S14; No), the item list providing system 100 determines whether the user performs a scrolling operation in the recommendation list (step S20).

[0061] When the user performs a scrolling operation (step S20; yes), the item list providing system 100 scrolls and displays the items in the recommendation list according to the content of the scrolling operation and in the order of recommendation in the recommendation list (step S21).

[0062] For example, as shown in FIG. 6(B), when two items RI1 and RI3 and the deleted item DI are displayed in the recommendation list 113, when the scroll button 114 is operated twice, as shown in FIG. 6(C), the recommendation order of the recommendation list 113 shifts by two stages and displays items RI3, RI4, and RI5. Furthermore, when the scroll button 114 is operated three times, as shown in FIG. 6(D), the recommendation order of the recommendation list 113 shifts by three stages and displays items RI6, RI8, and RI9. At this time, for example, item 7 corresponding to item RI7 is determined to be a low-interest item similar to item 2 corresponding to item RI2 of the non-need filtering operation, and the recommendation order is lowered to the lowest level. Therefore, the summary of item 7, that is, item RI7, is not displayed in FIG. 6(D). Moreover, when the recommendation list 113 is scrolled from the preset state, as shown in FIG. 6(C) and (D), the scroll button 115 for scrolling the recommendation list 113 in the reverse direction is displayed.

[0063] In addition, in this embodiment, the recommendation list is scrolled by the operation of the scroll buttons 114 and 115, but the recommendation list may be automatically scrolled (updated) by the browsing operation of the recommendation list such as the screen scroll operation. In addition, in the examples shown in FIG. 5 and FIG. 6, the recommendation list is scrolled in the left-right direction, but it may also be scrolled in the up-down direction, or in the up-down, left-right, and right-left directions.

[0064] After the processing of step S21 or when the user does not perform a scrolling operation on the recommendation list (step S20; No), the item list providing system 100 determines whether the user performs other operations on the item information and the recommendation list provided (step S22). When the user performs other operations (step S22; Yes), control corresponding to the operation (for example, display control of the item information of the selected recommendation item, etc.) is executed (step S23). When the user does not perform other operations (step S22; No) or after the processing of step S23, the process returns to step S14.

[0065] As described above, according to the project list providing system 100 of implementation form 1, in the project list providing system 100 having a server 10 and a terminal 20, the server 10 and the terminal 20 cooperate to perform the following processing: generate a list in which a plurality of items are arranged in the order of recommendation to the user, prompt the user with the items included in the generated list according to the recommended order arranged in the recommendation list, and when the user performs a non-demand filtering operation of specifying non-demand items from the prompted items, identify low-interest items that are similar to the non-demand items and are not prompted to the user among the items arranged in the recommendation list, and lower the recommendation order of the low-interest items in the recommendation list.

[0066] In this way, since the recommendation order (display order) of the items that the user is not expected to be interested in is lowered in the recommendation list based on the non-demand items selected by the user, when the user browses the recommended items in sequence, the possibility of the user seeing the items that the user is not expected to be interested in can be reduced.

[0067] Furthermore, since the recommendation order of the low-interest items is lowered, other items are displayed preferentially in the recommendation list. Therefore, since other items are relatively easy for the user to see, a recommendation list in which items expected to be of interest to the user are arranged can be presented.

[0068] Furthermore, since the order of recommendations in the recommendation list is changed within the scope of items that are not prompted to the user, the order of the recommendation list can be changed without the user's knowledge.

[0069] (Implementation form 2) Next, an example of a case where the server 10 in the item list providing system 100 manages the recommendation list and performs processing to lower the recommendation order of low-interest items in the recommendation list, that is, embodiment 2, is described. In embodiment 2, the server 10 is shown to "provide" the recommendation list to the terminal 20.

[0070] The server 10 of the second embodiment generates a recommendation list in which a plurality of items are arranged in the order of recommendation to the user. The server 10 provides the items included in the generated list to the terminal 20 according to the recommendation order arranged in the recommendation list, and displays the items on the screen of the terminal 20. The server 10 receives a report from the terminal 20 indicating the purpose of performing a non-needed screening operation in which non-needed items are specified from the items displayed on the screen in the terminal 20. Next, the server 10 specifies non-displayed items, i.e., low-interest items, which are similar to the non-needed items among the items arranged in the recommendation items and are not yet displayed on the screen of the terminal 20. Furthermore, the server 10 reduces the display priority of the low-interest items in the recommendation list and updates the recommendation list.

[0071] 7 is a flow chart showing an example of the recommendation list providing process executed by the server 10 according to Embodiment 2. The recommendation list providing process is executed by the processor 11 of the server 10 reading a program stored in the storage device 12 .

[0072] In the process of providing the recommendation list, the server 10 first determines whether a user's browsing request for an item of the server 10 is received from the terminal 20 (step S51). The user's browsing request for an item is sent, for example, according to the browsing operation of the item by the terminal 20. If no browsing request for an item is received (step S51; No), the process of providing the recommendation list ends.

[0073] If a browse request for an item is received (step S51; yes), the server 10 executes a recommendation list generation process (step S52) for generating a recommendation list to be provided to the terminal 20 of the user who made the browse request for the item. The recommendation list generation process may be the same as the process of the first embodiment shown in FIG. 4. The process of step S52 corresponds to the generation unit of the server 10.

[0074] When the recommendation list generation process is completed, the server 10 provides the recommendation list generated in step S52 together with the item information corresponding to the browsing request to the user's terminal 20 (step S53). For example, as shown in FIG. 5, the server 10 sends the web page data including the item information and the recommendation list to the terminal 20. In addition, the content of the item information corresponding to the browsing request can be the information of a specific item or the search result of the item as in the first embodiment. The process of step S53 is equivalent to the providing unit of the server 10.

[0075] In the second embodiment, the recommended items included in the recommendation list generated by the server 10 are provided to the terminal 20 in parts. In the recommendation list generation process of step S52, the server 10 generates a recommendation list including a specified number of items. The specified number can be any number, and can also vary depending on the number of similar items captured in the recommendation list generation process. Next, the server 10 provides the recommended items included in the generated recommendation list to the terminal 20 in parts. The number provided in parts can be any number as long as it is less than the above-mentioned specified number. It can also be a specified ratio of the specified number (for example, 30%). Next, when the recommendation list is scrolled on the terminal 20 side and all the provided items are browsed, the server 10 provides the subsequent items from the recommendation list.

[0076] FIG8 is a diagram of a method for managing a recommendation list in the server 10. As shown in FIG8, the server 10 generates a recommendation list based on a browse request for an item from the terminal 20. The recommendation list shown in FIG8 includes 12 items. The server 10 first manages the status of all items included in the generated recommendation list as "not provided" (not provided to the terminal 20) (FIG8(1)).

[0077] Next, the server 10 provides a portion of the items included in the recommendation list to the terminal 20. In FIG8 , items 1 to 5 in the recommendation list with the highest recommendation order up to the fifth are provided to the terminal 20. The server 10 updates the status of these items to “provided” (provided to the terminal 20) ( FIG8 (2)).

[0078] Next, the server 10 determines whether the non-need screening operation information indicating that the user has performed a non-need screening operation on a designated non-need item in the recommendation list provided to the user is received from the terminal 20 (step S54). The non-need screening operation information is a report indicating the purpose of the terminal 20 performing a non-need screening operation. The processing of step S54 is equivalent to the receiving unit of the server 10.

[0079] When receiving non-needed filtering operation information from the terminal 20 (step S54; yes), the server 10 sets the selected non-needed items to be non-displayed in the recommendation list (step S55). For example, the server 10 sends the data of a web page that updates the part of the displayed non-needed items to be non-displayed (for example, the deleted item DI shown in FIG. 6 (B)) to the terminal 20, and updates the recommendation list displayed on the terminal 20.

[0080] This can prevent the user from continuing to see items that are not needed. At this time, the items that are subjected to the non-need screening operation are stored in the storage device 12 of the server 10. Specifically, as non-needed items, they are stored and updated in the recommendation priority information corresponding to the user. Therefore, the non-needed items are not easily recommended or are not recommended to the user.

[0081] Next, the server 10 performs low-interest item identification processing: from the items included in the recommendation list, the low-interest items that are similar to the non-needed items screened by the user and are not provided to the user are identified (step S56). The processing of step S56 is equivalent to the identification part of the server 10.

[0082] In the low-interest item specific processing, for example, the server 10 compares the non-demand item with other items included in the recommendation list, and identifies similar items to the non-demand item included in the specific recommendation list.

[0083] The method of determining similar items can be, for example, based on the commonality of attribute information (type, manufacturer, state, size, color, region, price range, etc.), or based on a similarity table prepared in advance to classify the similarity of each item. In addition, the feature vector or feature amount of the elements (image data, text data, etc.) of each item can be obtained, and similar items can be determined based on the similarity of the feature vector or feature amount. In other words, similar items can be specified by any method.

[0084] Furthermore, the server 10 may also compare the items included in the recommendation list with the non-needed items to obtain similarity, and extract items within a predetermined threshold of similarity as similar items (low-interest items). Furthermore, items having a predetermined number or a predetermined ratio of the obtained similarity of the upper order may be extracted as similar items (low-interest items).

[0085] Items that have not been provided from the server 10 to the terminal 20 are not displayed in the terminal 20 and have not been browsed by the user. Therefore, in step S56, the unprovided items are approximated as undisplayed items, and low-interest items are identified from the unprovided items. In this way, since it is not necessary for the server 10 to obtain the browsing status of the recommended items from the terminal 20, the processing load can be suppressed.

[0086] In this regard, it is also conceivable that the number of recommended items provided from the server 10 to the terminal 20 at one time is different from the number of recommended items displayed at the terminal 20 at one time. For example, when the number of recommended items that can be displayed at the terminal 20 at one time is less than the number of recommended items provided from the server 10 to the terminal 20 at one time, there are items that have been provided but not displayed. In this case, it is also possible to obtain display information indicating whether the items are actually displayed in the terminal 20, and based on the display information, identify low-interest items from the items that are not displayed. In this case, when the items that have been provided to the terminal 20 and are not displayed are low-interest items, and when the recommendation list of that part is updated, it is sufficient to send the updated recommendation list to the terminal 20.

[0087] When a low-interest item is identified, the server 10 lowers the recommendation order of the low-interest item in the recommendation list (step S58). Next, the server 10 replenishes the recommended items according to the number of low-interest items in the recommendation list and updates the recommendation list (step S59). The server 10 adds the newly recommended items to the order of the items that have been prompted and the order of the low-interest items. In addition, the processing of steps S58 and S59 is the same as steps S18 and S19 of embodiment 1. The processing of steps S58 and S59 is equivalent to the update unit of the server 10.

[0088] For example, as shown in FIG8(2), at the stage where the server 10 provides the terminal 20 with items 1 to 5 included in the recommendation list, when the terminal 20 sends the non-needed filtering operation information of the third item to the server 10, from the 6th to 12th items not provided in the recommendation list, the items similar to the third item are specified as low-interest items. Then, the recommendation order of the specified low-interest items is lowered to the lowest level. At this time, the server 10 supplements the same number of recommended items as the low-interest items in an order higher than the low-interest items (for example, one order higher than the low-interest items). In this way, on the server 10 side, the recommendation list can be updated according to the user's non-needed filtering operation, and the recommendation list suitable for the user can be provided in sequence. In addition, the server 10 updates the status of the third item that performs the non-needed filtering operation to "delete" and updates the status of the low-interest items to "low-interest items" (FIG8(3)).

[0089] After processing step S59, or when no non-required filtering operation information is received from the terminal 20 (step S54; No), the server 10 determines whether scrolling operation information showing that the user has performed a scrolling operation in the recommendation list is received from the terminal 20 (step S60).

[0090] When receiving the scroll operation information from the terminal 20 (step S60; yes), the server system 10 scrolls the items of the recommendation list displayed on the screen of the terminal 20 according to the recommended order of the recommendation list according to the content of the scroll operation information (step S61). For example, the server 10 scrolls the recommendation list according to the recommended order and sends the updated web page data to the terminal 20, thereby updating the recommendation list displayed on the terminal 20.

[0091] For example, as shown in FIG8(3), when the server 10 provides items 1 to 5 included in the recommendation list to the terminal 20 and when the terminal 20 receives scroll selection operation information about the 6th and subsequent items from the server 10, the items 6 to 10 in the recommendation order are provided to the terminal 20. In this way, the recommended items can be provided in sequence from the server 10 to the terminal 20. The server 10 updates the status of the newly provided items to "provided" (provided to the terminal 20) (FIG8(4)).

[0092] After the processing of step S61, or when the scrolling operation information of the recommendation list is not received from the terminal 20 (step S60; No), the server 10 determines whether other operation information showing other operations performed by the user is received from the terminal 20 in the provided item information and the recommendation list (step S62). When other operation information is received from the terminal 20 (step S62; Yes), the server 10 executes control corresponding to the operation information (for example, display control of the item information of the selected recommendation item, update control of the web page, etc.) (step S63). When other operation information is not received from the terminal 20 (step S62; No), or after the processing of step S63, the processing returns to step S54.

[0093] FIG. 9 is a diagram showing an example of updating the recommendation order of the recommendation list generated in the server 10. For example, the case where the recommendation list consisting of items 1 to 12 is generated in the server 10 is described. The server 10 provides the recommended items, for example, five by five. After the recommendation list is generated, as shown in FIG. 9(A), items 1 to 5 are provided to the terminal 20. When the items are displayed three by three in the terminal 20, as shown in FIG. 9(A), items 1 to 3 are displayed to the user, and items 4 and 5 are not displayed.

[0094] Thereafter, when the user performs a one-step scrolling operation on the recommendation list, for example, as shown in FIG. 9(B) , item 4 is displayed.

[0095] Here, for example, when the user performs a non-needed filtering operation on item 3, as shown in FIG. 9(C), item 3 is deleted and becomes a non-needed item.

[0096] Next, from among the items 6 to 12 that are not provided, items similar to the non-needed items that are subjected to the non-needed screening operation are identified, for example, as shown in FIG. 9(D), the identified item 7 is extracted as a low-interest item.

[0097] Afterwards, as shown in FIG. 9(E), the same number of items 13 as the captured low-interest items are added to the order before the low-interest items as recommended items, and as shown in FIG. 9(F), the low-interest item, i.e., item 7, is moved to the bottom of the recommendation list.

[0098] In this way, the recommendation list is updated in the server 10 in a fluid manner according to the operation of the recommendation list in the terminal 20. The updated recommendation list is provided to the terminal 20 by obtaining a new item such as a scroll operation in the terminal 20. In this way, when the user browses the recommendation items in sequence, the recommended items can be appropriately provided to the user. Specifically, the possibility of the user viewing items that are not expected to be of interest can be reduced.

[0099] As described above, according to the server 10 of embodiment 2, a recommendation list is generated in which a plurality of items are arranged in the order of recommendation to the user, and the items included in the generated recommendation list are provided to the terminal 20 according to the recommendation order arranged in the recommendation list, and are displayed on the screen of the terminal 20, and a report indicating the purpose of performing a non-demand filtering operation in the terminal 20 to specify non-demand items from the items displayed on the screen is received from the terminal, and similar items that are similar to the non-demand items and are not displayed on the screen among the items arranged in the recommendation list, i.e., low-interest items, are identified, and the order of the low-interest items in the recommendation list is lowered.

[0100] In this way, based on the non-needed items selected by the user, the server 10 can lower the recommendation order (display order) of the items that are expected to be of no interest to the user in the recommendation list, and provide the recommended items from the recommendation list to the terminal 20. Therefore, when the user browses the recommended items in sequence, the possibility of the user viewing the items that are expected to be of no interest to the user can be reduced.

[0101] Furthermore, since the recommendation order of the low-interest items is lowered, other items are displayed preferentially in the recommendation list. Therefore, since other items are relatively easy for the user to see, a recommendation list in which items expected to be of interest to the user are arranged can be provided.

[0102] Furthermore, since the order of recommendations in the recommendation list is changed within the scope of items not provided to the user, the order of the recommendation list can be changed without the user's knowledge.

[0103] (Implementation form 3) Next, the example of Embodiment 3 is described in which the terminal 20 in the item list providing system 100 manages the recommendation list and performs processing to lower the recommendation order of low-interest items in the recommendation list. In Embodiment 2, the terminal 20 "displays" the recommendation list on the screen.

[0104] The terminal 20 of the third embodiment obtains from the server 10 a recommendation list in which a plurality of items generated in the server 10 are arranged in a recommended order. The terminal 20 can scroll and display the obtained list on the screen. The terminal 20 accepts a non-needed filtering operation of specifying non-needed items from the items arranged in the recommendation list and displayed on the screen. The non-displayed items that are similar to the non-needed items and are not displayed on the screen, i.e., low-interest items, are specified among the items arranged in the recommendation list. The terminal 20 lowers the order of the low-interest items in the recommendation list and updates the recommendation list.

[0105] 10 is a flow chart showing an example of the recommendation list display processing executed by the terminal 20 in the embodiment 3. The recommendation list display is executed by the processor 21 of the terminal 20 reading a program stored in the storage device 22.

[0106] During the display of the recommendation list, the terminal 20 first determines whether a user's browsing operation on the item is detected (step S71). The user's browsing operation on the item includes, for example, browsing the item provided by the server 10, accessing a website for search, selecting the item information on the website, searching, etc. If no browsing operation on the item is detected (step S71; No), the recommendation list display process ends.

[0107] If the browsing operation of the item is detected (step S71; yes), the terminal 20 sends a browsing request of the item corresponding to the browsing operation of the user on the server to the server (step S72). After that, the terminal 20 waits until the item information corresponding to the browsing request of the item and the recommendation list attached thereto are received from the server 10 (step S73). In addition, the recommendation list is generated by executing the recommendation list generation process shown in FIG. 4 in the server 10. The process of step S73 is equivalent to the acquisition unit of the terminal 20.

[0108] When receiving the project information and the recommended list from the server (step S73; yes), the terminal 20 displays the received project information and the recommended list on the screen (step S74). The terminal 20 displays the data of the web page including the project information and the recommended list as shown in FIG5, for example. In addition, the content of the project information is the same as in the first embodiment as long as it is the information of the specific project or the search result of the project. The processing of step S74 is equivalent to the display unit of the terminal 20.

[0109] In the third embodiment, the recommended items included in the recommendation list received from the server 10 are displayed on the terminal 20 in parts. The server 10 generates a recommendation list including an arbitrary number of items of a specified number. Then, the terminal 20 displays the items included in the received recommendation list in parts on the terminal 20. The number of parts displayed in parts can be any number as long as it is less than the above-mentioned specified number. It can also be a specified ratio of the specified number (for example, 30%). In addition, when the recommendation list is scrolled on the terminal 20 and all displayed items have been browsed, the terminal 20 displays the subsequent items from the recommendation list.

[0110] FIG. 11 is a diagram showing a method for managing a recommendation list in the terminal 20. As shown in FIG. 11, the terminal 20 sends a request for browsing an item to the server 10 according to the item browsing operation of the user. The server 10 generates a recommendation list according to the browsing request and sends the generated recommendation list to the terminal 20. At this time, the server 10 determines the similarity between the recommended items included in the recommendation list, and also sends the determination result, that is, the similarity information between the recommended items. The determination method for the similarity between the recommended items is the same as that in the above-mentioned embodiment, and it can be determined by the similarity of attribute information, feature vector, feature quantity, etc. Therefore, the similarity information can be a similarity table that classifies the similarity of each item, or it can be information representing the feature vector of each item. By sending the similarity information in advance, it is not necessary to calculate the similarity between the recommended items on the terminal 20 side, which can reduce the processing burden of the terminal 20 and seek to speed up the processing.

[0111] The recommendation list sent from the server 10 shown in FIG11 includes 12 items. The terminal 20 displays a portion of the items (e.g., 3 items each) included in the recommendation list on the terminal 20. In FIG11, the recommendation order in the recommendation list is displayed as items 1 to 3 from the top 3. The terminal 20 manages the status of the displayed items as "displayed" (displayed on the terminal 20) and manages the other items as "not displayed" (not displayed on the terminal 20) (FIG11(1)).

[0112] Next, the terminal 20 determines whether the non-needed filtering operation of specifying non-needed items in the displayed recommendation list has been accepted by the user (step S75). The processing of step S75 is equivalent to the acceptance unit of the terminal 20.

[0113] When the non-needed filtering operation has been accepted (step S75; yes), the terminal 20 sets the selected non-needed items to be non-displayed in the recommendation list (step S76). For example, the terminal 20 sets the non-needed part (such as the deleted item DI shown in Figure 6 (B)) to be non-displayed, and updates the recommendation list. This can prevent the user from continuing to see the items that the user does not need. At this time, the items that have been subjected to the non-needed filtering operation are stored in the storage device 22 of the terminal 20. Specifically, they are stored as non-needed items and updated to the recommendation priority information corresponding to the user. Therefore, the non-needed items will not be easily recommended or will not be recommended to the user in the future.

[0114] Next, the terminal 20 performs low-interest item identification processing, that is, from the items included in the recommendation list, identifies low-interest items that are similar to the non-needed items that have been screened by the user and are not displayed to the user (step S77). The processing of step S77 is equivalent to the identification part of the terminal 20.

[0115] In the low-interest item specific processing, for example, the terminal 20 compares the non-demand item with other items included in the recommendation list that are not displayed to the user, and specifies similar items to the non-demand item included in the recommendation list as low-interest items.

[0116] Similar items to non-required items can be identified based on similarity information (similarity table, feature vector, etc.) received from the server 10 together with the recommendation list. For example, based on the similarity information, the items included in the recommendation list and the non-required items can be compared to obtain similarity, and items with similarities within a predetermined threshold can be extracted as similar items (low-interest items). In addition, items with a predetermined number or a predetermined ratio of the obtained similarities can be extracted as similar items (low-interest items).

[0117] In addition, when the terminal 20 detects a non-needed screening operation, the information of the selected non-needed item can be sent to the server 10, and the server 10 can perform similar item identification and low interest item identification. The method for determining similar items in the server can be, for example, the method of embodiment 2. In this case, it is not necessary to obtain similarity information from the server 10 in advance.

[0118] Furthermore, when similarity information is not received in advance, similarity information between recommended items can be obtained when a non-needed screening operation is detected by the terminal 20. Furthermore, the similarity table can be obtained at other times other than when the recommendation list is obtained.

[0119] The items not displayed on the terminal 20 have not been browsed by the user. In this embodiment, in order to change the recommendation order of the recommendation list that the user has not browsed, in step S77, low-interest items are specified from the items not displayed.

[0120] When a low-interest item is identified, the terminal 20 lowers the recommendation order of the low-interest item in the recommendation list (step S79). The processing of step S79 is the same as step S18 of embodiment 1. Step S79 corresponds to the updating unit of the terminal 20.

[0121] Next, the terminal 20 sends information of the items after non-demand selection, i.e., non-demand selection information, and an item replenishment request to request to replenish the recommended items according to the number of low-interest items in the recommendation list to the server 10 (step S80). By sending the non-demand item information to the server 10, the recommendation priority information of each user can be updated in the server 10 based on the non-demand item information. The non-demand screening operation information becomes a report of the non-demand items sent from the terminal 20 to the server 10. When a new recommendation list is generated in the server 10, the recommendation priority information is referred to, and the recommendation order of the non-demand items based on the user's past non-demand screening operation is lowered to generate a recommendation list, thereby generating a recommendation list suitable for the user. That is, by the report of the non-demand item from the terminal 20, the server 10 can lower the priority of recommending the reported item.

[0122] Afterwards, the terminal 20 waits until the supplementary item information corresponding to the item supplement request is received from the server 10 (step S81). The item supplement request may include information that can specify the number of recommended lists or low-interest items.

[0123] When receiving the item supplement request from the terminal 20, the server 10 extracts the newly added recommended items in the recommendation list and sends the item information of the extracted recommended items to the terminal 20. For example, the server 10 only needs to extract the same number of new recommended items as the low-interest items. The method of extracting the supplemented items only needs to use the same algorithm as when the recommendation list is generated. For example, it only needs to supplement the recommended items that are not included in the initially generated recommendation list, the items recommended at the next point, and the recommended items that are not equivalent to the low-interest items.

[0124] When the supplementary item information corresponding to the item supplement request is received from the server 10 (step S81; yes), the terminal 20 supplements the item corresponding to the received supplementary item information as a new recommended item and updates the recommendation list (step S82). In step S82, for example, the recommendation order of the low-interest item in the recommendation list is reduced to the lowest level, and the new recommended item is added to the recommendation list in a higher order than the low-interest item. In other words, the terminal 20 adds the new recommended item to the order of the items that have been prompted and between the order of the low-interest items. In this way, the new items corresponding to the number of low-interest items can be added to the recommendation list, and the new items can be recommended in a higher order than the low-interest items.

[0125] After processing step S82, or when accepting a non-needed screening operation (step S75; No), the terminal 20 determines whether it is detected that the user is performing a scrolling operation in the recommendation list (step S83).

[0126] When a scrolling operation is detected (step S83; yes), the terminal 20 scrolls the items of the recommendation list displayed on the screen of the terminal 20 according to the content of the scrolling operation and the recommendation order of the recommendation list (step S84). For example, the terminal 20 scrolls the recommendation list according to the recommendation order and displays the updated web page data, and updates the recommendation list displayed on the terminal 20.

[0127] After the processing of step S84, or when the scrolling operation of the recommendation list is not detected (step S83; No), the terminal 20 determines whether the user performs other operations in the displayed item information and the recommendation list (step S85). When other operations are detected (step S85; Yes), the terminal 20 executes control corresponding to the detected operation (for example, display control of the item information of the selected recommendation item, update control of the web page, etc.) (step S86). When other operations are not detected (step S85; No), or after the processing of step S86, the processing returns to step S75.

[0128] In the third embodiment, as shown in FIG. 11 (1), when items 1 to 3 included in the recommendation list are displayed on the terminal 20, and a scroll operation is performed to browse the fourth item on the terminal 20, for example, the terminal 20 updates the status of the displayed item to "displayed" (displayed on the terminal 20) (FIG. 11 (2)). In addition, in this embodiment, as shown in FIG. 5, since the items in the recommendation list are displayed three by three, items 2 to 4 are displayed on the terminal 20 after the scroll operation.

[0129] Furthermore, for example, as shown in FIG. 11 (2), when items 2 to 4 included in the recommendation list are displayed on the terminal 20 and a non-need filtering operation is performed on the third item, the third item is set to be non-displayed on the terminal 20, and the status of the third item after the non-need filtering operation is updated to "deleted".

[0130] When performing a non-needed screening operation on the terminal 20, non-needed item information and an item supplement request are sent to the server 10. In addition, the terminal 20 specifies items similar to the third item from the fifth to twelfth items not displayed in the recommendation list as low-interest items. The terminal 20 updates the status of the specified low-interest items to "low-interest items" (Figure 11 (4)). In Figure 11 (4), the fifth and eighth items are specified as low-interest items.

[0131] Furthermore, the terminal 20 lowers the recommendation order of the specific low-interest item to the lowest level, and supplements the items (here, two items) corresponding to the supplementary item information received from the server 10 with an order higher than the low-interest item (for example, one order higher than the low-interest item) to update the recommendation list (FIG. 11 (5), (6)). In this way, in the third embodiment, the terminal 20 can update the recommendation list according to the non-demand screening operation of the user, and can display the recommendation list suitable for the user in order.

[0132] FIG. 12 is a diagram showing an example of updating the recommendation order of the recommendation list in the terminal 20. For example, the description is given of a case where a recommendation list consisting of items 1 to 12 is generated in the terminal 20. The terminal 20 displays the recommendation items three by three, for example. After receiving the recommendation list from the server 10, as shown in FIG. 12(A), items 1 to 3 are displayed on the terminal 20, while items 4 to 12 are not displayed.

[0133] Thereafter, when the user performs a one-step scrolling operation on the recommendation list, for example, item 4 is displayed as shown in FIG. 12(B) .

[0134] Here, for example, when the user performs a non-needed filtering operation on item 3, as shown in FIG. 12(C), item 3 is deleted and becomes a non-needed item.

[0135] Next, from the undisplayed items, i.e., items 5 to 12, items similar to the non-needed items after the non-needed screening operation are identified, for example, as shown in FIG. 12(D), the identified items 5 and 7 are captured as low-interest items.

[0136] Afterwards, as shown in Figure 12(E), items 13 and 14, which are the same number as the captured low-interest items, are added from server 10 to the order before the low-interest items as recommended items, and as shown in Figure 12(F), the low-interest items, namely items 5 and 7, are moved to the bottom of the recommendation list.

[0137] In this way, the recommendation list is updated in the terminal 20 in a fluid manner according to the operation of the recommendation list in the terminal 20. The updated recommendation list is displayed in sequence by the display operation of new items such as the scroll operation in the terminal 20. In this way, when the user browses the recommendation items in sequence, the recommended items can be appropriately provided to the user. Specifically, the possibility of the user viewing items that are not expected to be of interest can be reduced.

[0138] As described above, according to the terminal 20 of implementation form 3, a recommendation list in which a plurality of items are arranged in a recommended order is obtained from the server 10, and the obtained recommendation list is displayed in a scrollable manner on the screen, and a non-demand filtering operation of specifying non-demand items from among the items arranged in the recommendation list and displayed on the above screen is accepted, and similar items similar to the non-demand items among the items arranged in the recommendation list and non-display items that have not yet been displayed on the screen, i.e., low-interest items, are specified, and the order of the low-interest items in the list is lowered and updated.

[0139] In this way, based on the non-needed items selected by the user, the recommended order (display order) of the items that are expected to be of no interest to the user can be lowered under the guidance of the terminal 20, and the recommended items from the recommended list can be displayed to the terminal 20. Therefore, when the user browses the recommended items in sequence, the possibility of the user viewing the items that are expected to be of no interest to the user can be reduced.

[0140] Furthermore, since the recommendation order of the low-interest items is lowered, other items are displayed preferentially in the recommendation list. Therefore, other items are relatively easy for the user to see, and a recommendation list in which items expected to be of interest to the user are arranged can be provided.

[0141] Furthermore, since the order of recommendations in the recommendation list is changed within the scope of items not displayed to the user, the order of the recommendation list can be changed without the user's knowledge.

[0142] (Variation Example) In addition, the present invention is not limited to the above-mentioned embodiments, and various changes and applications are possible. For example, a part of the above-mentioned embodiments may be omitted, replaced, or any arbitrary structure may be added.

[0143] Furthermore, instead of changing the order of recommendation of low-interest items in the recommendation list, the display format of the low-interest items may be changed. For example, the display format of the recommendation list may be changed so that the low-interest items are not obvious. For example, the display size of the low-interest items in the list may be reduced or excluded from the recommendation list. By doing so, when the user browses the recommended items in sequence, the possibility of the user seeing items that are not expected to be of interest to the user can be reduced.

[0144] When browsing the items included in the recommendation list (e.g., touching or clicking on a link to detailed information), it is inferred that the user is interested in the item, so in the recommendation list, a high-interest item similar to the item and not prompted (not displayed) is specified, and the recommendation order of the high-interest item in the recommendation list is increased. In this way, in the recommendation list, the possibility of the user seeing the item of interest increases, and the user is less likely to see the item of disinterest, so the item can be appropriately recommended to the user.

[0145] In the above-mentioned embodiments, when a non-needed item is selected, a new recommended item is added when the recommendation order of the non-needed item is lowered. This is not limited to this, and the recommendation order of the non-needed item may be lowered without adding a new recommended item. That is, the process of adding a new recommended item in step S19 of FIG. 3, step S59 of FIG. 7, and step S82 of FIG. 10 may be omitted.

[0146] The process of adding new recommended items to the recommendation list can also be performed at different points in time. For example, when accepting the user's scrolling operation on the recommendation list, the new recommended items can be added to the recommendation list. In this way, when the user browses the recommendation list in sequence, the recommended items can be added in sequence, so that the recommended items can be endlessly provided.

[0147] The server 10 or the terminal 20 does not rely on a dedicated device and can be implemented using a common computer. For example, the server 10 and the terminal 20 that execute the above-mentioned processing can be configured by installing a program from a recording medium storing the program for executing the above-mentioned functions on the computer on the computer. In addition, one server 10 can also be configured by a plurality of computers working in cooperation.

[0148] Furthermore, any method for supplying the program to the computer is optional. For example, it may be supplied via a communication line, a communication network, a communication system, etc. For example, a non-temporary computer-readable recording medium storing the program for executing the above functions may be distributed.

[0149] Furthermore, when the OS (Operation System) provides a part of the above functions, it is sufficient to provide the functions other than those provided by the OS through a program.

[0150] The above embodiments are provided to facilitate understanding of the present invention, but are not intended to limit the present invention. The flowcharts, sequences, and various elements and their configurations, materials, conditions, shapes, and sizes described in the embodiments are not limited to those shown, and may be appropriately changed. Furthermore, the structures shown in different embodiments may be partially replaced or combined with each other.

[0151] (Invention realized by this embodiment) As described above, this embodiment realizes the invention shown below.

[0152] (Note 1) A system for providing a project list, which is provided with a server and a terminal, and The server and the terminal cooperate to perform the following processing: generating a list of multiple items in the order of recommendation to the user; Prompt the user with the items included in the generated list according to the order in which they are arranged; When the user performs a non-demand screening operation to specify a non-demand item from the items presented, identify low-interest items that are similar to the non-demand item and have not yet been presented to the user from among the items arranged in the list; Lower the order of the above low interest items in the above list.

[0153] (Note 2) A server comprising: A generating unit, which generates a list in which a plurality of items are arranged in the order of recommendation to the user; a providing unit, which provides the items included in the generated list to the terminal according to the order in which the items are arranged in the list, and displays the items on the screen of the terminal; A receiving unit, which receives a report from the terminal, the report indicating that a non-demand screening operation of specifying non-demand items from the items displayed on the screen has been performed in the terminal; A specifying section, which specifies similar items that are similar to the non-demand items in the items arranged in the recommendation list and are not yet displayed in the screen, that is, low-interest items; and An update section that lowers the order of the above-mentioned low-interest items in the above-mentioned list.

[0154] (Note 3) As in the server of Note 2, The report further includes: display information showing which of the items included in the list is displayed on the screen of the terminal; and The items not displayed in the above-mentioned display information are set as the above-mentioned non-display items.

[0155] (Note 4) For example, the server in Note 2 or 3, The items that have not been provided to the terminal are set as the non-display items.

[0156] (Note 5) A server as in any one of Notes 2 to 4, wherein Re-recommend new items that are not similar to the above non-needed items and are not included in the above list; and In the above list, the above new item is added between the order of the items already provided to the above terminal and the order of the above low-interest items.

[0157] (Note 6) A terminal having: An acquisition unit, which acquires a list of a plurality of items arranged in a recommended order from a server; A display unit, which displays the above-obtained list in a scrollable manner on the screen; An accepting section accepts a non-demand screening operation of specifying non-demand items from the items arranged in the above list and displayed in the above screen; A specifying section, which specifies similar items that are similar to the non-demand items among the items arranged in the list and are non-displayed items that have not yet been displayed in the screen, i.e., low-interest items; and An update section that lowers the order of the above-mentioned low-interest items in the above-mentioned list.

[0158] (Note 7) As the terminal in Appendix 6, By reporting the non-required items to the server, the server lowers the priority of recommending the reported items.

[0159] (Note 8) As a terminal in Note 6 or 7, By reporting the non-required items to the server, the server can identify similar items in the list that are similar to the non-required items.

[0160] (Note 9) A terminal as in any one of Notes 6 to 8, wherein Obtaining from the server together with the list a table of similarities between the items arranged in the list; and From the above table, the above similarity between each of the above non-display items and the above non-required items is obtained.

[0161] (Note 10) A terminal as in any one of Notes 6 to 9, wherein Obtaining from the server together with the list the feature vector of each item arranged in the list; and Based on the feature vector, the similarity between each of the non-display items and the non-demand items is calculated.

[0162] (Note 11) As the terminal of Note 9 or 10, The similarity calculated above is compared with a specified threshold value to identify the similar items, or the items whose similarity calculated above is a specified number or a specified proportion of the upper level are identified as the similar items and the low-interest items.

[0163] (Note 12) A terminal as in any one of Notes 6 to 10, wherein Cause the server to re-recommend new items that are not similar to the above non-required items; and Append the above new items to the above list in order of higher interest than the above low interest items.

[0164] (Note 13) A project list providing method is a project list providing method in a project list providing system having a server and a terminal, and The server and the terminal cooperate to perform the following processing: generating a list of multiple items in the order of recommendation to the user; Prompt the user with the items included in the generated list according to the order in which they are arranged; and When the user performs a non-demand screening operation of specifying a non-demand item from the items presented, identify low-interest items that are similar to the non-demand item and have not yet been presented to the user from among the items arranged in the list; Lower the order of the above low interest items in the above list.

[0165] (Note 14) A program that enables a computer to function as: A generating unit, which generates a list in which a plurality of items are arranged in the order of recommendation to the user; a providing unit, which provides the items included in the generated list to the terminal according to the order in which the items are arranged in the list, and displays the items on the screen of the terminal; A receiving unit, which receives a report from the terminal, the report indicating that a non-demand screening operation of specifying non-demand items from the items displayed on the screen has been performed in the terminal; A specifying section, which specifies similar items that are similar to the non-demand items among the items arranged in the list and are non-displayed items that have not yet been displayed in the screen, i.e., low-interest items; and An update section that lowers the order of the above-mentioned low-interest items in the above-mentioned list.

[0166] (Note 15) A program that enables a computer to function as: An acquisition section, which acquires a list of multiple items arranged in a recommended order; A display unit, which displays the above-obtained list in a scrollable manner on the screen; An accepting section accepts a non-demand screening operation of specifying non-demand items from the items arranged in the above list and displayed in the above screen; A specifying section, which specifies similar items that are similar to the non-demand items among the items arranged in the list and are non-displayed items that have not yet been displayed in the screen, i.e., low-interest items; and An update section that lowers the order of the above-mentioned low-interest items in the above-mentioned list. [Industrial Applicability]

[0167] According to the present invention, an item list providing system, a server, a terminal, an item list providing method, and a program can be provided which can appropriately recommend items to users.

[0168] 10: Server 11,21: Processor 12,22: Memory Device 13,23: Communication interface 14,24: Input devices 15,25: Output devices 20: Terminal 30: Communication Network 100: Project list providing system 110: Web browser 111: Project name 112: Project details 113: Recommended List 114,115: Scroll button DI: Deleted Items ds: non-demand selection button RI1,R12,RI3,RI4,RI5,RI6,RI8,RI9:Project (recommended project) rs: Undo button S11~S16,S18~S23,S51~S56,S58~S63,S71~S77,S79~S86,S121~S123: Steps

Claims

1. A project list providing system, comprising a server and a terminal, and performing the following processing: Retrieving a plurality of projects corresponding to a user's browsing requirements, and generating a list arranging the retrieved plurality of projects in the order recommended to the user based on each user's priority information; Displaying the projects included in the generated list sequentially, piece by piece, on the terminal screen by scrolling the screen according to the order in the list; When the user performs a non-demand filtering operation to specify non-demanded projects from the suggested projects, identifying projects that have not yet been shown to the user based on the browsing status of the list on the terminal, and identifying low-interest projects in the list that are similar to the non-demanded projects and have not yet been shown to the user; Lowering the order of the low-interest projects in the list.

2. A project list providing server, comprising: a generation unit that extracts a plurality of projects corresponding to a user's browsing requirements, and generates a list arranging the extracted plurality of projects in order of recommendation to the user based on priority information of each user; a providing unit that provides the projects included in the generated list to the terminal by scrolling the terminal screen and displaying them sequentially in parts on the terminal screen according to the order of arrangement in the list; a receiving unit that receives a report from the terminal indicating that a non-demand filtering operation of specifying non-demand projects from the projects displayed on the screen has been performed on the terminal; a specifying unit that specifies non-display projects, i.e., low-interest projects, that are similar to the non-demand projects in the projects arranged in the list but have not yet been displayed on the screen; and an updating unit that reduces the order of the low-interest projects in the list; and the report further includes: display information that displays which projects are displayed on the terminal screen among the projects included in the list. Set the items not displayed in the above information to the "not displayed" items.

3. A project list providing server, comprising: a generation unit that extracts a plurality of projects corresponding to a user's browsing requirements for projects, and generates a list arranging the extracted plurality of projects in the order recommended to the user based on priority information of each user; a providing unit that provides the projects contained in the generated list to the terminal by scrolling the terminal screen and displaying them sequentially in parts on the terminal screen according to the order of arrangement in the list; a receiving unit that receives a report from the terminal indicating that a non-demand filtering operation of specifying non-demand projects from the projects displayed on the screen has been performed on the terminal; a specifying unit that specifies non-display projects, i.e., low-interest projects, that are similar to the non-demand projects in the projects arranged in the list but have not yet been displayed on the screen; and an updating unit that reduces the order of the low-interest projects in the list and sets projects that have not yet been provided to the terminal as non-display projects.

4. For servers requesting item 2 or 3, new items that are dissimilar to the aforementioned non-required items and are not included in the aforementioned list are re-recommended; and in the aforementioned list, the aforementioned new items are added between the order of items already provided to the aforementioned terminals and the order of the aforementioned low-interest items.

5. A project list providing terminal, comprising: an acquisition unit that acquires from a server a list of a plurality of projects arranged in a recommended order; a display unit that displays the acquired list scrollably on a screen; a processing unit that processes a non-demand filtering operation of specifying non-demanded projects from the projects arranged in the list and displayed on the screen; a selection unit that, based on the scrolling status of the list, selects non-displayable projects that are not yet displayed on the screen, and selects similar projects in the list that are similar to the non-demanded projects and are also non-displayable projects, i.e., low-interest projects; and an update unit that lowers the order of the low-interest projects in the list.

6. As in request item 5, the terminal, by reporting the aforementioned non-required items to the aforementioned server, causes the aforementioned server to reduce the priority of recommending the reported items.

7. As in request item 5, the terminal, by reporting the aforementioned non-required items to the aforementioned server, causes the aforementioned server to identify similar items in the aforementioned list that are similar to the aforementioned non-required items.

8. The terminal of request item 5, wherein the similarity table between the list and the items arranged in the list is obtained from the server; and from the table, the similarity between each of the non-display items and the non-required items is calculated.

9. The terminal of request item 5, wherein the feature vectors of the list and each item arranged in the list are obtained together from the server; and based on the feature vectors, the similarity between each of the non-display items and the non-required items is calculated.

10. For terminals requesting item 8 or 9, the similarity calculated above is compared with a specified threshold to identify the similar items, or the items with a similarity calculated above that is a specified number or a specified proportion of the previous level are identified as the similar items and the low-interest items.

11. For any of the requests in items 5 to 9, the terminal shall cause the server to re-recommend new items that are not similar to the non-demanded items; and add the new items to the list in order of priority over the low-interest items.

12. A method for providing a project list, which is a project list providing system having a server and a terminal, and performs the following processing: Retrieving a plurality of projects corresponding to a user's browsing requirements for projects, and generating a list arranging the retrieved plurality of projects in the order recommended to the user based on each user's priority information; Providing the user with a prompt regarding the projects included in the generated list by scrolling the screen of the terminal, displaying them sequentially in parts on the screen of the terminal according to the order of arrangement in the list; and when the user performs a non-demand filtering operation to specify non-demanded projects from the prompted projects, identifying projects that have not yet been prompted to the user based on the browsing status of the list on the terminal, and identifying low-interest projects in the list that are similar to the non-demanded projects and have not yet been prompted to the user; and reducing the order of the low-interest projects in the list.

13. A computer program providing a list of items, which enables a computer to function as follows: a generation unit that extracts a plurality of items corresponding to a user's browsing requirements, and generates a list that arranges the extracted plurality of items in order of recommendation to the user based on priority information for each user; a providing unit that provides the items included in the generated list to the terminal by scrolling the terminal screen and displaying them sequentially in parts on the terminal screen according to the order in which the list is arranged; a receiving unit that receives a report from the terminal indicating that a non-demand filtering operation of specifying non-demand items from the items displayed on the screen has been performed on the terminal; a specifying unit that specifies non-display items, i.e., low-interest items, that are similar to the non-demand items in the list and have not yet been displayed on the screen; and an updating unit that reduces the order of the low-interest items in the list; and the report further includes: display information that shows which items are displayed on the terminal screen among the items included in the list. Set the items not displayed in the above information to the "not displayed" items.

14. A computer program providing a list of items, which enables a computer to function as: a generation unit that extracts a plurality of items corresponding to a user's browsing requests for items, and generates a list that arranges the extracted plurality of items in the order recommended to the user based on each user's priority information; a providing unit that provides the items contained in the generated list to the terminal by scrolling the terminal screen and displaying them sequentially in parts on the terminal screen according to the order arranged in the list; a receiving unit that receives a report from the terminal indicating that a non-demand filtering operation of specifying non-demand items from the items displayed on the screen has been performed on the terminal; a specifying unit that specifies non-display items, i.e., low-interest items, that are similar to the non-demand items in the list and have not yet been displayed on the screen; and an updating unit that lowers the order of the low-interest items in the list and sets items that have not yet been provided to the terminal as non-display items.

15. A computer program providing a list of items, which enables a computer to function as: an acquisition unit that acquires a list of a plurality of items arranged in a recommended order; a display unit that scrollably displays the acquired list on a screen; an acceptance unit that accepts a non-demand filtering operation from the items arranged in the list and displayed on the screen to specify non-demand items; a selection unit that, based on the scrolling status of the list, selects non-display items not yet displayed on the screen, and selects similar items in the list that are similar to the non-demand items and are also non-display items, i.e., low-interest items; and an update unit that lowers the order of the low-interest items in the list.

Images