Information processing system, information processing method, and program

Abstract

To provide an information processing system which proposes an optimal commodity for a user, an information processing method, and a program. An information processing system is configured to: acquire a set including multiple genres which are related to each other; select a related genre which is a genre related to a genre to which an item purchased or browsed by a user belongs, based on the acquired set; and acquire one of items belonging to the selected related genre, as an item to be recommended.

Description

[Technical Field]

[0001] This invention relates to information processing systems, information processing methods, and program products. [Previous Technology]

[0002] For example, in the sale of goods via the Internet, there are systems that recommend products in response to the user's actions. Furthermore, as recommendations, products that are more likely to be purchased when grouped with products that the user has previously bought or browsed are selected.

[0003] Patent Document 1 discloses a method for recommending products based on user activity history derived from purchase or browsing records. [Prior Art Documents] [Patent Documents]

[0004] [Patent Document 1] International Publication No. 2017 / 104064 [Summary of the Invention]

[0005] [The problem the invention aims to solve]

[0006] A product that is frequently purchased in combination with another product may not necessarily be the best product for the user.

[0007] This invention was developed in view of the aforementioned problems, and its purpose is to provide a technology for proposing a product that is better for the user. [Means for solving the problems]

[0008] In order to solve the above-mentioned problems, the information processing system of the present invention includes: a link acquisition means for acquiring a set of multiple types containing mutual links; a type selection means for selecting, based on the aforementioned acquired set, the type related to the type to which the user has purchased or browsed is the link type; and a recommendation object acquisition means for acquiring any one of the items belonging to the aforementioned link types that have been selected in the previous version as a recommendation object.

[0009] Furthermore, the information processing method of the present invention includes: a step of obtaining a set containing a plurality of mutually related types; a step of selecting, based on the aforementioned obtained set, the type related to the type to which the user has purchased or browsed, i.e., the related type; and a step of obtaining, as a recommendation object, any one of the items belonging to the aforementioned related types that have been selected.

[0010] Furthermore, the program described in this invention enables the computer to perform the following functions: a connection acquisition means for acquiring a set of multiple types containing mutual connections; a type selection means for selecting, based on the aforementioned acquired set, the type related to the type to which the user has previously purchased or browsed, i.e., the connection type; and a recommendation object acquisition means for acquiring any one of the items belonging to the aforementioned connection types that have been selected, as a recommendation object.

[0011] In one aspect of the present invention, the means of obtaining the aforementioned recommended object is to obtain the item that has been purchased or viewed the most times from among the items belonging to the aforementioned related types that have been selected in the prior.

[0012] In one aspect of the present invention, the means of obtaining the aforementioned recommended items is to obtain the items that have been purchased or viewed the most times and are in stock from among the items belonging to the aforementioned related types that have been selected in the prior.

[0013] In one aspect of the present invention, the aforementioned means of obtaining recommended items can be used to obtain items that are sold within a predetermined period as recommended items.

[0014] In one embodiment of the present invention, the prior history acquisition means can acquire purchase history or browsing history from other stores that are different from the store that the prior user is currently accessing; the prior type selection means can select, based on the prior set, the type that is related to the type of the items that the prior user has purchased or browsed in other stores in the prior, namely the prior association type; the prior recommendation object acquisition means can acquire any item from the store that the prior user is currently accessing and that belongs to any of the items in the prior association type that has been selected in the prior as a prior recommendation object.

[0015] In one embodiment of the present invention, it further includes: a history acquisition means for acquiring a plurality of purchase histories containing combinations of items that have been purchased together, or a plurality of browsing histories containing combinations of items that have been viewed together; and a aforementioned association acquisition means for determining a set of a plurality of mutually related types containing the aforementioned types based on the type to which the items constituted by combining the plurality of combinations contained in the aforementioned plurality of purchase histories or the aforementioned plurality of browsing histories belong.

[0016] In one embodiment of the present invention, the prior history acquisition means acquires prior purchase history or prior browsing history from a plurality of stores; the prior type selection means selects, based on the previously determined set of priors, the type related to the type of items that the prior user has purchased or browsed in the prior stores, i.e., the prior association type; the prior recommendation object acquisition means acquires any item from the prior stores that belongs to any item in the previously selected prior association type as a prior recommendation object. [Effects of the Invention]

[0017] Through this invention, a product that is better for the user can be proposed.

Implementation Method

[0019] Hereinafter, embodiments of the present invention will be described based on the drawings. Repeated descriptions of elements marked with the same symbols are omitted. This embodiment describes an information processing system that enables e-commerce transactions between multiple stores. In this information processing system, products are proposed as items to users who have accessed a particular store.

[0020] Figure 1 is an illustration of an example of an information processing system according to an embodiment of the present invention. The information processing system includes an information processing server 1 and client devices 2. The information processing server 1 is connected to one or more client devices 2 via a network.

[0021] The information processing server 1 includes: a processor 11, a memory unit 12, a communication unit 13, and an input / output unit 14. Furthermore, the information processing server 1 is a server computer. The processing of the information processing server 1 can also be achieved by multiple server computers. The client device 2 includes: a processor 21, a memory unit 22, a communication unit 23, and an input / output unit 24. The client device 2 is a personal computer, a smartphone, or a tablet terminal.

[0022] Processors 11 and 21 operate according to programs stored in memory units 12 and 22. Furthermore, processors 11 and 21 control communication units 13 and 23, and input / output units 14 and 24. In addition, the aforementioned programs can be provided via the Internet or other means, or stored in computer-readable memory media such as flash memory or DVD-ROM.

[0023] Memory units 12 and 22 are composed of memory elements such as RAM and flash memory, and external memory devices such as hard disk drives. Memory units 12 and 22 store the above-mentioned programs. Furthermore, memory units 12 and 22 store information or calculation results input from processors 11 and 21, communication units 13 and 23, and input / output units 14 and 24.

[0024] The communication units 13 and 23 are for communicating with other devices and are composed of integrated circuits that implement wireless LAN or wired LAN. The communication units 13 and 23, based on the control of the processors 11 and 21, input information received from other devices to the processors 11 and 21 or the memory units 12 and 22, and send the information to the other devices.

[0025] Input / output units 14 and 24 are composed of a video controller that controls the display output device or a controller that obtains data from the input device. Input devices include keyboards, mice, touch panels, etc. Input / output units 14 and 24, based on the control of processors 11 and 21, output display data to the display output device and obtain data input by the user through the input device. The display output device is, for example, a monitor device connected externally.

[0026] Next, the functions provided by the information processing system will be explained. Figure 2 is a block diagram of the functions implemented by the information processing system. Functionally, the information processing system includes: a complete history acquisition unit 51, a relationship type determination unit 52, a relationship item determination unit 53, a repurchase possibility acquisition unit 54, a user history acquisition unit 55, a repurchase candidate acquisition unit 56, a relationship candidate acquisition unit 57, a list addition unit 58, an output unit 59, and a shopping cart control unit 60. These functions are mainly implemented by the processor 11 included in the information processing server 1 executing the program stored in the memory unit 12 and controlling the communication unit 13, etc. Furthermore, part of the function of the output unit 59 can be implemented by the processor 21 included in the client device 2 executing the program stored in the memory unit 22 to control the communication unit 23 and the input / output unit 24. The related candidate acquisition department 57 functionally includes: a type utilization department 61 and an item utilization department 62. Functionally, the type utilization department 61 includes a type selection department 66 and an item selection department 67, and the item utilization department 62 includes an item selection department 69.

[0027] The overall record acquisition unit 51 acquires at least one of the purchase records and browsing records. Each purchase record contains: information indicating that a user has made a purchase, and a combination of items that were purchased together. Each browsing record contains: information indicating that a user has browsed, and a combination of items that were browsed together. For example, items that were browsed within a predetermined period (e.g., on the same day) can be considered as items that were browsed together. The purchase records and browsing records are stored in the memory unit 12 for multiple users using the information processing system, such as all users. The overall record acquisition unit 51 can also acquire all of the purchase records and browsing records stored in the memory unit 12, or it can acquire the purchase records and browsing records of a specific store.

[0028] The related type determination unit 52 determines the set of multiple related types based on the type of the item to which it belongs by combining multiple combinations contained in multiple purchase records or multiple browsing records that have been obtained.

[0029] The related item determination unit 53 determines a set of multiple related items based on the multiple combinations contained in the multiple purchase records or multiple browsing records that have been obtained.

[0030] The repurchase probability acquisition unit 54 calculates the repurchase probability for each item based on the already acquired purchase history.

[0031] The user history acquisition unit 55 acquires at least one of the following: purchase history containing items that have been purchased by the user, and browsing history containing items that have been viewed by the user.

[0032] The repurchase candidate acquisition unit 56 selects at least one of the items included in the user's purchase history as a repurchase candidate.

[0033] The related candidate acquisition unit 57 selects at least one item that is different from the items included in the user's purchase history and browsing history as a related candidate. The method of acquiring items as repurchase candidates in the repurchase candidate acquisition unit 56 is different from the method of selecting items as related candidates in the related candidate acquisition unit 57.

[0034] The type utilization unit 61 included in the related candidate acquisition unit 57 selects the types related to the types of items that the user has previously purchased or browsed, and acquires any item from the selected type as a recommended object, that is, a related candidate.

[0035] The type selection unit 66 included in the type utilization unit 61 selects the type related to the type of the items that the user has purchased or browsed, based on the acquired set.

[0036] The item selection unit 67 included in the type utilization unit 61 acquires any item included in the selected type as a recommended candidate, i.e., a related candidate. More specifically, the item selection unit 67 acquires the item that has been purchased or viewed the most times among the items in the selected type as a related candidate. The item selection unit 67 may also acquire items that have started selling within a specified period as related candidates. Here, the specified period may be a period of the past month or week, etc.

[0037] The item utilization unit 62 included in the related candidate acquisition unit 57 selects items that are related to items that the user has previously purchased or browsed, and acquires the selected items as recommended items, i.e., related candidates.

[0038] The item selection unit 69 included in the item utilization unit 62 obtains items related to items that the user has previously purchased or browsed, based on the already obtained set, as related candidates.

[0039] The list addition section 58 adds the selected repurchase candidates and related candidates to the list. The list addition section 58 adds the repurchase candidates and related candidates to the list in such a way that the repurchase candidates are placed before the related candidates.

[0040] Output unit 59 displays images of items included in the list, arranged in positions corresponding to their order. If output unit 59 is configured solely as an information processing server 1, it displays the images by sending image data to client device 2. Furthermore, if output unit 59 is also included in client device 2, it displays the images on the display device of client device 2.

[0041] The shopping cart control unit 60 adds items that have been included in the list and have been displayed and have been indicated by the user to the shopping cart.

[0042] Next, the details of the information processing system will be explained. Figure 3 is a flowchart of an example of the processing of the overall resume acquisition unit 51, the related type determination unit 52, the related item determination unit 53, and the repurchase possibility acquisition unit 54. The processing shown in Figure 3 only needs to be performed once in advance, but it can also be repeated, for example, at a predetermined interval.

[0043] First, the overall record acquisition unit 51 acquires the purchase and browsing records of a plurality of users (step S101). The overall record acquisition unit 51 can acquire the purchase and browsing records stored in the memory unit 12 for a specific store, regardless of the user, or it can acquire the purchase and browsing records stored in the memory unit 12 for all stores managed by the information processing system. Furthermore, the acquired purchase and browsing records can also be those from the past year.

[0044] Next, the association type determination unit 52 extracts combinations of items that were previously purchased together from the acquired purchase history, and extracts combinations of items that were previously viewed together from the acquired browsing history (step S102). Then, the association type determination unit 52 obtains the type to which each item in the extracted combination belongs (step S103). Strictly speaking, the types can have a hierarchical structure, and the association type determination unit 52 can obtain the lowest level type (the third level type if there are three levels of types). The type used here can be a type in a specific store or a type common to all stores.

[0045] Then, the relationship type determination unit 52 determines the set of mutually related types based on the types to which each item in the combination belongs (step S104). The relationship type determination unit 52 counts the sets of types to which the items in the combination belong, and determines the set of mutually related types based on the number of the counted sets of types. For example, if the number of the counted sets of types is greater than a threshold, the relationship type determination unit 52 may determine that set of types as a set of mutually related types.

[0046] Furthermore, the related item determination unit 53 determines the set of mutually related items based on the items included in the extracted combinations (step S105). For example, the related item determination unit 53 may count the number of times a combination occurs and determine the set of mutually related items based on the counted number of times. For example, if the number of times a combination occurs is greater than a threshold, the related item determination unit 53 may determine the items included in that combination as a set of mutually related items.

[0047] In addition, the relationship type determination unit 52 can also determine the set of mutually related types of the set of items that have been determined by the relationship item determination unit 53, and the set of items to which each item in the set belongs.

[0048] Furthermore, the repurchase probability acquisition unit 54 calculates the repurchase probability for each item (step S106). For example, the repurchase probability can also be the percentage of users who have purchased the calculated item multiple times, which is considered the repurchase rate. In addition, the repurchase probability acquisition unit 54 can also store items whose calculated repurchase probability is greater than a predetermined condition, i.e., a threshold, as items with high repurchase probability in the memory unit 12.

[0049] Furthermore, the repurchase probability can also be predicted using a learning model. The repurchase probability acquisition unit 54 acquires the repurchase probability based on the past purchase dates of the items purchased by the user. Specifically, the repurchase probability acquisition unit 54 uses a learning model that takes the past purchase dates of the items as input and outputs the repurchase probability of the items to acquire the repurchase probability of the items. The learning model is generated using known machine learning algorithms such as neural networks, and is generated through supervised machine learning by using the relationship between the past purchase dates of the items purchased by the user and the existence or absence of repurchases by the user as teacher data. The repurchase probability acquisition unit 54 can also store items in the memory unit 12 that meet the predetermined conditions for repurchase probability from the items included in the user's purchase history as items with high repurchase probability. For example, if the learning model outputs the repurchase probability numerically, then items with a repurchase probability greater than a predetermined condition, i.e., a threshold, can be considered items with a high repurchase probability. Similarly, if the learning model outputs "yes" or "no" as the repurchase probability, then items with a repurchase probability meeting a predetermined condition (e.g., "yes") can be considered items with a high repurchase probability.

[0050] There is a certain relationship between the past purchase date of an item and its repurchase probability. For example, items recently purchased by a user or items purchased a long time ago tend to have a lower repurchase probability because the user's purchase desire is lower at the current point in time. On the other hand, items that users purchase regularly tend to have a higher repurchase probability in the next purchase period. By using a learning model that studies whether or not an item's past purchase date has been linked to repurchase, the user's repurchase probability can be determined with high accuracy.

[0051] Furthermore, the input data for the learning model is not limited to past purchase dates of items. For example, the input data could also be the repurchase rate. This allows for predictions reflecting the actual repurchase outcomes of each item. For example, the input data could also be the number of past purchases of items by the user. This allows for predictions reflecting the actual purchase outcomes of items by each user. For example, the input data could also be the number of items previously purchased by the user. This allows for predictions reflecting the period between the previous purchase and the next purchase, which varies with the number of previous purchases. For example, the input data could also be the price of the item. This allows for predictions reflecting the lower probability of repurchase of high-priced items. For example, the input data could also be the repurchase rate of the item's type. Therefore, even for items with relatively low actual purchase rates, it is still possible to predict the repurchase rate of a category that reflects the correlation between the item's repurchase rate and the repurchase rate. Furthermore, multiple input data points from the aforementioned input data can be used as input data for a learning model. By using a learning model that has learned from the aforementioned input data and the relationship between the user's repurchase likelihood and the actual repurchase rate, the likelihood of a user's repurchase can be determined with high accuracy.

[0052] Next, we will explain the processing when a user accesses a store's sales page in the information processing system. Figures 4 to 6 are illustrations of one example of the sales-related processing for a user. Figures 4 to 6 illustrate the outlines of the processing of the user profile acquisition unit 55, the repurchase waitlist acquisition unit 56, the related waitlist acquisition unit 57, the list addition unit 58, the output unit 59, and the shopping cart control unit 60.

[0053] First, the user history acquisition unit 55 identifies the user who has accessed the information processing server 1 (step S201) and acquires the purchase history and browsing history of the store accessed by the user (step S202).

[0054] When a purchase history has already been obtained (step S203, Y), the repurchase candidate acquisition unit 56 selects items with a high probability of repurchase from the items included in the already obtained purchase history as repurchase candidates, and the list addition unit 58 adds the selected items to the list (step S204). Furthermore, the type utilization unit 61 included in the related candidate acquisition unit 57 selects candidate items from a plurality of items displayed in the store based on the purchase history and related types, and the list addition unit 58 adds the selected candidate items to the list (step S205). The item utilization unit 62 included in the related candidate acquisition unit 57 selects candidate items from a plurality of items displayed in the store based on the purchase history and related items, and the list addition unit 58 adds the selected candidate items to the list (step S206). Here, the list addition section 58 adds items in such a way that the items added in step S204 are in a higher order than the items added in steps S205 and S206. Once the processing of steps S204 to S206 has been performed, the processing moves to step S219.

[0055] A detailed explanation of the process in step S205 will be provided. Figure 7 is an illustration of an example of the process of the type utilization unit 61. First, the type selection unit 66 included in the type utilization unit 61 obtains the types of each item contained in the action history formed by the purchase history or browsing history (step S301). For example, in step S205, the action history is the purchase history. Then, the type selection unit 66 selects the type (related type) that is related to the obtained type based on the set of multiple mutually related types determined by the related type determination unit 52 (step S302).

[0056] The item selection unit 67 selects the highest-ranking item from the items belonging to the related type and displayed in the store as a candidate item (step S303). The ranking can be set based on the sales quantity or sales amount in that type. Furthermore, the item selection unit 67 removes items from the selected items that are duplicates of items selected from other activity records (step S304). Then, the item selection unit 67 selects items with remaining stock from the selected items as candidate items (step S305), and the list addition unit 58 adds the candidate items to the list.

[0057] The processing in step S206 will also be explained. Figure 8 is an illustration of one example of the processing in the item utilization unit 62. First, the item selection unit 69 included in the item utilization unit 62 selects items that are related to each item in the action history and are displayed in the store, based on the set of multiple items that have been determined by the related item determination unit 53 (step S401). The item selection unit 69 deletes duplicate items from the selected items (step S402) and selects items that are still in stock among the selected items as candidate items (step S403). The list addition unit 58 adds candidate items to the list.

[0058] Here, if the purchase history is not obtained in step S202 (N in step S203), then the process moves to step S207.

[0059] When the browsing history has been obtained (Y in step S207), the type utilization unit 61 included in the related candidate acquisition unit 57 selects items as candidate items based on the browsing history and related types, and the list addition unit 58 adds the selected candidate items to the list (step S208). The details of step S208 are that the action history is changed to the browsing history in the process shown in FIG7. The item utilization unit 62 included in the related candidate acquisition unit 57 selects items as candidate items based on the browsing history and related items, and the list addition unit 58 adds the selected candidate items to the list (step S209). The details of the process in step S209 are that the action history is changed to the browsing history in the process shown in FIG8. Once the processes of steps S208 and S209 are performed, the process moves to step S219.

[0060] Here, if the browsing history is not obtained in step S202 (N in step S207), then the process moves to step S210.

[0061] The processing described in steps S210 to S217 is the processing when the user has not purchased or viewed any records in the stores they access.

[0062] In step S210, the user history acquisition unit 55 acquires the user's purchase history and browsing history in other stores (step S210). Here, if neither the purchase history nor the browsing history can be acquired (N in step S211), then since recommendations cannot be made based on the purchase history and browsing history, the list addition unit 58 adds the items included in the sales ranking of the stores accessed by the user to the list (step S212).

[0063] On the other hand, if the purchase history has been obtained (Y in step S211 and Y in step S213), the type utilization unit 61 included in the related candidate acquisition unit 57 selects candidate items from the items displayed in other stores based on the purchase history and related types in those stores, and adds the selected candidate items to the list (step S215). The processing in step S215 is to change the action history to the purchase history in other stores in the processing shown in FIG7. If the purchase history has not been obtained (Y in step S211 and N in step S213), then step S215 is skipped.

[0064] Furthermore, if browsing history has been obtained (Y in step S211 and Y in step S216), the type utilization unit 61 included in the related candidate acquisition unit 57 selects candidate items from the items displayed in other stores based on browsing history and related types in those stores, and adds the selected candidate items to the list (step S217). The processing in step S217 is to change the action history to browsing history in other stores as shown in Figure 7. If browsing history has not been obtained (Y in step S211 and N in step S216), then step S217 is skipped, and the process proceeds to step S219.

[0065] Here, specific examples are given for items that are added to the list by steps S202 to S217.

[0066] Figure 9 is an illustration of an example of the relationship between purchase history in store S and items added to the list. Store S is assumed to be the store accessed by the user. In the case shown in Figure 9, the user's purchase history exists in store S, and the items included in the purchase history are kitchen paper towels A, toilet paper B, diapers C, and mineral water D. The list includes: items acquired through the repurchase candidate acquisition section 56 (corresponding to the first selection method), namely kitchen paper towels A, toilet paper B, and diapers C (see "Repurchase Proposal" in Figure 9); items selected through the type utilization section 61 included in the related candidate acquisition section 57 (corresponding to the second selection method), namely milk powder E, baby food F, and thermos flask G (see "Proposal Due to Related Type" in Figure 9); and items selected through the item utilization section 62 included in the related candidate acquisition section 57 (corresponding to the second selection method), namely mineral water H and a 12-bottle pack of mineral water J (see "Proposal Due to Related Items"). It is also assumed in Figure 9 that the items located at the top have a higher priority.

[0067] Kitchen paper towels A, toilet paper B, and diapers C, which have been added to the list, are items with a higher probability of repurchase from the user's purchase history at store S. Bottled water D, which has a lower probability of repurchase, was not added to the list.

[0068] The diaper C series belongs to the "diaper" type, while the milk powder E, baby food F, and thermos bottle G series belong to the "milk powder," "baby food," and "baby supplies" types, respectively. The "diaper" type is interconnected with the "milk powder," "baby food," and "baby supplies" types. The type utilization unit 61 of the related candidate acquisition unit 57 selects the highest-ranking item among the "diaper" related types, namely milk powder E, baby food F, and thermos bottle G, as candidates for proposal. Here, if the type utilization unit 61 does not have stock of the highest-ranking item, it will not select the item as a candidate. In this case, the type utilization unit 61 may also select the highest-ranking item among the items that are still in stock as a candidate. Furthermore, the Item Utilization Department 62 of the Related Candidate Acquisition Department 57 can also select mineral water H and mineral water J 12-bottle bundles related to mineral water D as candidates for proposal. Here, the Item Utilization Department 62 does not select items that are not in stock as candidates.

[0069] By selecting items to be proposed based not only on the items themselves but also on the types of those related, the range of items proposed to the user increases, and the likelihood that the proposed items are more relevant to the user's situation increases. This improves usability by increasing the likelihood of items being purchased and reducing the hassle of item retrieval for the user. Furthermore, the information processing server, which has been inputting items that the user has previously purchased or viewed, automatically outputs items to be proposed by referring to a set of multiple interconnected types. This allows for high-speed and high-precision retrieval of items to be proposed to the user. Also, since the number of types is less than the number of items, the amount of data processed by the information processing server is reduced, thus lowering the processing load.

[0070] Figure 10 is an illustration of an example of the relationship between purchase history and browsing history in store S and items added to the list. In the case shown in Figure 10, there is no purchase history for the user in store S, but there is browsing history. The items included in the browsing history are coffee K and makeup remover L. The type "makeup remover" to which makeup remover L belongs is related to the type "sunscreen" to which sunscreen O belongs, so items that would be selected as candidates would be selected in this way. In this case, the selection of candidate items is also carried out through two methods (which can also correspond to the first selection method and the second selection method): the selection of proposed items caused by the interrelated types of type utilization section 61 and the selection of proposed items caused by the interrelated items of item utilization section 62. Furthermore, even if a user's purchase history exists in store S, alternative selections can still be made based on browsing that history.

[0071] Figure 11 is an illustration of an example of the relationship between purchase history, browsing history, and items added to the list. In the case shown in Figure 11, the user's purchase history and browsing history do not exist in store S, but purchase history and browsing history exist in other stores. The purchase history in other stores includes diapers C, and the browsing history includes makeup remover L. In this case, the type utilization unit 61 of the related candidate acquisition unit 57 selects candidates using two methods: candidate selection based on purchase history and candidate selection based on browsing history. Furthermore, even if the user's purchase history or browsing history exists in store S, candidate selection can still be made based on purchase history or browsing history in other stores.

[0072] Furthermore, the information processing server 1 can select candidate items in store S based on purchase history or browsing history in other stores using various selection methods. For example, if store S displays items included in the purchase history or browsing history of users in other stores, items identical to those included in the purchase history or browsing history of users in other stores can also be selected as candidate items in store S. At this time, among the items included in the purchase history of users in other stores, items with a high probability of repurchase can also be selected as candidate items in store S. For example, the type utilization unit 61 included in the related candidate acquisition unit 57 can also select candidate items in store S based on the purchase history or browsing history of users in other stores by using interconnected types. For example, the item utilization unit 62 included in the related candidate acquisition unit 57 can also select candidate items in store S based on the purchase history or browsing history of users in other stores, by means of interconnected items.

[0073] In the stores that the user is currently accessing, candidate items are selected based on the purchase or browsing history of users in other stores. This allows for the proposal of suitable items by taking into account the purchase or browsing history of users in other stores. In this way, the likelihood of an item being purchased can be increased, while reducing the hassle of searching for items for the user, thereby improving usability.

[0074] In step S219, the output unit 59 outputs a proposal screen containing the list to a display device owned by or connected to the client device 2. Here, the output unit 59 outputs the proposal screen in a manner that the candidate items included in the list are arranged in positions corresponding to their order. For example, the proposal screen is a screen displayed on the webpage of a store accessed by the user.

[0075] Figure 12 is an illustration of an example of a proposal screen that has been output. The proposal screen is configured with a plurality of add buttons 81 and a checkout button 84, and a plurality of items included in the list. Each item is configured with an individual add button 82 and a checkbox 83.

[0076] The individual add button 82 is a button used by the user to indicate the need to add the corresponding item to the shopping cart. The checkbox 83 is a button used to select the corresponding item. The multiple add buttons 81 are buttons used to indicate the need to add the item corresponding to the selected checkbox 83 to the shopping cart when pressed. The checkout button 84 is a button used to indicate the start of the purchase process for items that have been added to the shopping cart. The client device 2 sends information indicating this fact to the information processing server 1 once either the individual add button 82 or the checkout button 84 is pressed. The client device 2 sends information indicating the item corresponding to the selected checkbox 83 at the time of pressing, as well as information indicating that the button has been pressed, to the information processing server 1 once the multiple add buttons 81 are pressed.

[0077] In the proposal screen, candidate items selected and added to the same list through multiple methods, such as repurchase candidate items and related candidate items, are displayed together. This concentrates the user's references in one place, reducing the load on the referenced products. Furthermore, the information processing server sends candidate items selected through multiple methods to the client device as data from the same list, rather than separate lists. This reduces the amount of data sent from the information processing server to the client device, thus reducing communication load and speeding up the display and processing of the proposal screen on the client device.

[0078] Steps S221 to S229 are the processing steps taken when the user interacts with the proposal screen. The following is an explanation of this processing.

[0079] In step S221, the shopping cart control unit 60 determines whether the individual add button 82 has been pressed by the user. If the individual add button 82 has been pressed (Y in step S221), the shopping cart control unit 60 adds the item corresponding to the pressed individual add button 82 to the shopping cart (step S222). Then, proceeding to step S225, the output unit 59 changes the individual add button 82 of the item added to the shopping cart to the quantity input field 85 (see Figure 13). The change to the quantity input field 85 can be achieved by the client device 2 executing a program that sends the data along with the proposal screen, thereby replacing the currently displayed individual add button 82 with the quantity input field 85. Alternatively, the information processing server 1 can send the data of the proposal screen that has replaced the individual add button 82 with the quantity input field 85 to the client device 2, and the client device 2 will then display the proposal screen.

[0080] Figure 13 is an illustration of one example of a proposal screen after an item has been added to the shopping cart. In the example of Figure 13, it is shown that, regarding the item in the upper left corner of the items proposed in Figure 12, when the individual add button 82 has been pressed, the individual add button 82 changes into the quantity input field 85.

[0081] If an individual add button 82 is not pressed (N in step S221), the shopping cart control unit 60 determines whether multiple add buttons 81 have been pressed (step S223). If multiple add buttons 81 have been pressed (Y in step S223), the shopping cart control unit 60 adds the items that have been checked in the corresponding checkbox 83 to the shopping cart (step S224). Then, in step S225, the output unit 59 changes the individual add button 82 of the items that have been added to the shopping cart to the quantity input field 85.

[0082] Once the process of step S225 is performed, the processes after step S221 will be repeated.

[0083] On the other hand, if the multiple addition button 81 is not pressed (N in step S223), the shopping cart control unit 60 determines whether the quantity input field 85 has been changed (step S226). If the quantity input field 85 has been changed (Y in step S226), the shopping cart control unit 60 changes the quantity in the shopping cart corresponding to the changed quantity input field 85 (step S227). Thereafter, the processing after step S221 is repeated.

[0084] If the quantity input field 85 is not changed (step S226 N), the shopping cart control unit 60 determines whether the checkout button 84 has been pressed (step S228). If the checkout button 84 has been pressed (step S228 Y), the shopping cart control unit 60 performs the purchase-related processing for the items in the shopping cart, more specifically, performs the checkout and delivery-related processing (step S229). On the other hand, if the checkout button 84 has not been pressed (step S228 N), the processing after step S221 is repeated.

[0085] Although embodiments of the present invention have been described, the application of the present invention is not necessarily limited to these embodiments. For example, the item may be not only a physical product that is sold, but also content that is sent as data. [Simplified Explanation of the Diagram]

[0018] [Figure 1] Illustration of the hardware configuration of the information processing system described in the embodiment of the present invention. [Figure 2] Block diagram of the functions implemented by the information processing system. [Figure 3] Flowchart of an example of the processing of the overall history acquisition unit, the related type determination unit, the related item determination unit, and the repurchase possibility acquisition unit. [Figure 4] Illustration of an example of the processing related to sales to users. [Figure 5] Illustration of an example of the processing related to sales to users. [Figure 6] Illustration of an example of the processing related to sales to users. [Figure 7] Illustration of an example of the processing of the type utilization unit. [Figure 8] Illustration of an example of the processing of the item utilization unit. [Figure 9] Illustration of an example of the relationship between the purchase history in store S and the items added to the list. [Figure 10] Illustration of an example of the relationship between the purchase history and browsing history in store S and the items added to the list. [Figure 11] Illustration of an example of the relationship between the purchase history and browsing history and the items added to the list. [Figure 12] An illustration of one example of the output proposal screen. [Figure 13] An illustration of one example of the proposal screen after items have been added to the shopping cart.

Claims

1. An information processing system comprising: a link acquisition means for acquiring a set of a plurality of mutually related types; a type selection means for selecting, based on the aforementioned acquired set, types related to the types to which items previously purchased or viewed by the user belong, i.e., link types; and a recommendation object acquisition means for acquiring any one of the items belonging to the aforementioned link types that have been selected as a recommendation object.

2. The information processing system as described in claim 1, wherein, The method for obtaining recommended items is to select the items that have been purchased or viewed the most times from among the items in the related categories of the previously selected items, and then use them as recommended items.

3. The information processing system as described in claim 1, wherein, The method for obtaining recommended items is to select the items that have been purchased or viewed the most times and are in stock from the items belonging to the related categories of the previously selected items.

4. The information processing system as described in Request 1, wherein, The method for obtaining recommended items is to acquire items that are put on sale within a specified period as recommended items.

5. The information processing system described in any of claims 1 to 4, wherein, The method for obtaining prior records involves acquiring purchase or browsing history from other stores that are different from the store currently accessed by the prior user. The method for selecting prior types is based on the prior set and selects the types related to the items that the prior user has purchased or browsed in other stores in the prior set, i.e., the prior relationship types. The method for obtaining prior recommended items involves acquiring any item from the prior store that the prior user is currently accessing and that belongs to any of the prior relationship types that have been selected in the prior set, as a prior recommended item.

6. The information processing system described in any of claims 1 to 4, wherein, It also includes: means of obtaining records, which are used to obtain multiple purchase records that each contain a combination of items that have been purchased together, or multiple browsing records that each contain a combination of items that have been viewed together; and means of obtaining the aforementioned relationships, which are used to determine a set of multiple types containing the aforementioned interrelated relationships based on the type to which the items constituted by combining the multiple combinations contained in the aforementioned multiple purchase records or the multiple browsing records belong.

7. The information processing system as described in claim 6, wherein, The method for obtaining prior records involves acquiring multiple prior purchase records or multiple prior browsing records from multiple stores. The method for selecting prior types involves selecting the types related to the types of items that the prior user has purchased or browsed in the multiple prior stores, i.e., the prior relationship types, based on the previously determined set of prior records. The method for obtaining prior recommendation objects involves acquiring any item from the multiple prior stores that belongs to any item in the previously selected prior relationship type as a prior recommendation object.

8. An information processing method comprising: obtaining a set of a plurality of mutually related types; selecting, based on the aforementioned obtained set, a type related to the type to which the user has previously purchased or browsed, i.e., a related type; and obtaining, as a recommendation, any one of the items belonging to the aforementioned related types that have been selected.

9. A computer program product, characterized in that it enables the computer to perform the following functions: a means of obtaining a set of a plurality of mutually related types; a means of selecting, based on the aforementioned obtained set, a type related to the type to which the user has previously purchased or browsed items belongs, i.e., a related type; and a means of obtaining a recommended item, which obtains any one of the items belonging to the aforementioned related types that have been selected as a recommended item.

Images