JP2012103909A - Recommendation information transmission device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide useful recommendation information without requiring introduction of a recommendation system for each shop even when user related commodity information cannot be sufficiently collected in a single shop.SOLUTION: A recommendation information transmission device 1 includes user related commodity information reception means 101 for receiving user related commodity information transmitted from multiple shop devices 2, related-information-between-commodities creation means 103 for creating related information between commodities to be used to recommend a commodity from the received user related commodity information, commodity information reception means 105 for receiving commodity information from each of the shop devices, recommendation information extraction means 107 for extracting recommendation information for the commodity information from the related information between commodities and recommendation information transmission means 109 for transmitting the recommendation information extracted by the recommendation information extraction means 107 to each of the shop devices 2.

Description

  The present invention relates to a technique for providing recommendation information based on information obtained from a plurality of stores operating shopping sites on the Internet.

  In recent years, in stores that operate shopping sites on the Internet, it is widely used to recommend (recommend) a product to a certain user using user-related product information such as product purchase history information and product evaluation information. It is done.

  For example, in Patent Document 1 below, a time series pattern related to item purchase is generated from purchase histories of a plurality of users, and an accurate item recommendation can be performed for each user by referring to the time series pattern. An information processing apparatus is disclosed.

JP 2008-176398 A

  However, as in the above-described prior art, a certain amount of user-related product information is required to obtain useful recommendation information, which is useful in small stores where user-related product information cannot be collected sufficiently. There was a problem that it was difficult to obtain recommended information. In general, it is difficult to introduce a recommendation system that creates and presents product recommendation information using user-related product information due to cost and technical issues, especially in small stores. It seems that there are many.

  Therefore, an object of the present invention is to eliminate the need to introduce a recommendation system for each store, and to provide users with useful recommended information even if sufficient user-related product information cannot be collected only at a certain store. It is to be.

  The recommended information transmitting device of the present invention includes user-related product information receiving means for receiving user-related product information, which is information related to products based on user behavior transmitted from a plurality of store devices, and the received user-related product information. Product-related information creating means for creating product-related information, which is information related to products based on user behavior, and product information receiving means for receiving product information from a store device, Recommended information extracting means for extracting related product information corresponding to the product information from the related information between products as recommended information, and recommended information transmitting means for transmitting the recommended information extracted by the recommended information extracting means to the store apparatus It is characterized by having.

  In the recommended information transmission method of the present invention, the computer receives the user-related product information receiving step for receiving user-related product information that is information related to the product based on the user behavior transmitted from the plurality of store apparatuses, An inter-product related information creating step for creating inter-product related information, which is information for associating products based on user behavior, used for recommending a product from the user-related product information, and a product that receives product information from a store device An information receiving step, a recommended information extracting step for extracting related product information corresponding to the product information as recommended information from the inter-product related information, and a recommendation information extracted in the recommended information extracting step is transmitted to the store device And a recommendation information transmitting step.

  Thus, in the recommendation information transmitting apparatus and method of the present invention, the inter-product related information is created based on the user-related product information obtained from a plurality of stores, and the product information is transmitted to the store device that has transmitted the product information. Recommendations based on inter-product related information created by collecting user-related product information from multiple stores, even if the store cannot sufficiently collect user-related product information to transmit recommendation information extracted from related information Information can be utilized. Further, since the recommendation information is itself created by the recommendation information transmitting apparatus of the present invention, each store can provide recommendation information to the user without introducing a recommendation system for each store.

  In the recommendation information transmitting apparatus according to the present invention, the user-related product information is information in which at least a user identifier is associated with a product identifier corresponding to a product purchased or browsed by the user in the past.

  As described above, in the recommended information transmitting device of the present invention, since the product identifier associated with the user identifier is used as the user-related product information from a plurality of store devices, the product name assigned to each store is different even for the same product. And being recognized as a different product.

  The recommendation information transmitting apparatus according to the present invention is characterized in that the user-related product information is information associated with store information in addition to a product identifier.

  As described above, in the recommended information transmitting apparatus of the present invention, since store information is associated with a product identifier, it is possible to determine whether or not a store that receives recommended information using the information handles the product. It becomes.

  It should be noted that other categories such as programs corresponding to the above-described modes and more specific modes described below are also included in the present invention.

  As described above, according to the present invention, it is not necessary to introduce a recommendation system for each store, and useful recommendation information is provided to the user even if sufficient user-related product information cannot be collected only at a certain store. It becomes possible.

The functional block diagram which shows the structure of embodiment of this invention. The sequence diagram which shows the process sequence in embodiment of this invention. The figure which illustrates the user related goods information storage means in the embodiment of the present invention. The figure which illustrates user related merchandise information in an embodiment of the present invention. The figure which illustrates the related information between goods in embodiment of this invention. The figure which illustrates the related information between goods in embodiment of this invention. The figure which illustrates the graph between goods in the embodiment of the present invention. The figure which illustrates the page transmitted to the user in the embodiment of the present invention. The sequence diagram which shows the process sequence in embodiment of this invention. The figure which illustrates user related merchandise information in an embodiment of the present invention. The figure which illustrates the related information between goods in embodiment of this invention. The figure which illustrates the related information between goods in embodiment of this invention.

Hereinafter, embodiments for carrying out the present invention will be described with reference to the drawings.
[1. Embodiment 1]
As shown in FIG. 1, the present embodiment relates to a recommendation information transmission device (hereinafter also referred to as “this device”) 1 in which a computer transmits recommendation information and a plurality of store apparatuses 2 to N that receive recommendation information. The apparatus 1 and the store apparatuses 2 to N have, as general computer configurations, at least an arithmetic control unit 5 such as a CPU, a storage device 6 such as an external storage device (HDD or the like) or a main memory, and an illustration. Communication means 7 (such as a LAN adapter) with a communication network (such as the Internet or a cellular phone network) that does not. Note that the user terminal T1 is a personal computer, a mobile phone, or the like, and recommended information transmitted from the apparatus 1 is displayed on an installed web browser.

  In the apparatus 1, a predetermined computer program (not shown) stored (installed) in advance in the storage device 6 controls the arithmetic control unit 5 so that the elements (101, 201,...) Shown in FIG. Realize. Among these elements, information storage means can be realized in the storage device 6 in any format such as temporary storage of various databases, files, array variables, and setting values. Each means other than the storage means is a processing means for realizing / executing a function / action of information processing described below.

[2. Action)
An outline of the operation procedure of the present apparatus 1, the store apparatuses 2 to N, and the user terminal T1 configured as shown in FIG. 1 is shown in the sequence diagram of FIG. Note that although there are actually a plurality of store apparatuses, the description will be given mainly using the store apparatus 2 which is one of them as an example.

[2-1. Creation of related information between products)
First, the creation of product related information essential for extracting recommendation information will be described.

  The user terminal T1 makes a browsing request to the store apparatus 2 of the store that operates the shopping site in order to access the shopping site on the Internet (step S1). Next, the browsing request receiving unit 205 of the store apparatus 2 receives a browsing request from the user terminal T1, and the page transmitting unit 211 transmits page data to the user terminal T1 (step S2).

  Collecting user-related product information of the store apparatus 2 using user-related product information as user-related product information obtained from the exchange of browsing requests and page data transmissions repeatedly performed between the user terminal T1 and the store apparatus 2 The means 201 collects and stores it in the user related product information storage means 213 (step S3).

  Here, the user-related product information represents information related to a product based on user behavior, and the product information based on user behavior such as product purchase or product browsing performed by the user on the Internet, and the product information uniquely. This is information that associates information to be represented for each user. Specifically, the product identifier may be a user identifier, product purchase history information that is information related to products that the user has purchased in the past, product browsing history information that is information related to products that the user has browsed in the past, and product identifiers. These user-related product information is related to the user's consumption behavior on the Internet, and is considered to reflect the user's interest and interest in those products. The product identifier can be obtained by referring to a product database storing a correspondence table of products handled in each store and a product identifier corresponding to the product, which is not shown.

  FIG. 3 shows a specific example of the user-related product information storage unit 213. The user-related product information storage unit 213 stores a user identifier 2131 that identifies a user, purchased product purchase history information 2132, and a product identifier 2133 that uniquely represents the product. For example, in the example of FIG. 3, it represents that the user whose user identifier is TENPO2A has purchased products A, B, and G, and their product purchase history information (here, A etc. is the product name) and A product identifier is stored in association with each other. Here, only the product purchase history information is stored as the product information based on the user's behavior, but both the product purchase history information and the product browsing history information may be stored together. You may remember.

  Here, the user identifier 2131 may be anything as long as it can uniquely recognize a user for each store, may be a user ID issued for each store, or for users accessing each store apparatus 2 to N. Cookies (browser cookies) issued by the store apparatuses 2 to N may be used. The product identifier 2133 is preferably a standardized product that can be uniquely specified as a product even across stores. For example, a JAN code (a standard established by the Japanese Industrial Standards consisting of 12-digit numbers) displayed on a product as a barcode. A product display) is preferably used.

  Next, the user related product information transmitting unit 203 of the store apparatus 2 transmits the user related product information stored in the user related product information storage unit 213 to the apparatus 1 (step S4). In addition, as a timing which transmits to this apparatus 1, you may make it transmit only the user relevant merchandise information collected that day at the time decided once a day, for example, and it transmits whenever new information is collected. May be. It should be noted that the user-related product information once transmitted should not be transmitted repeatedly.

  Here, at least a user identifier and a product identifier associated therewith are transmitted to the apparatus 1 as user-related product information. In the processing to be described later, the product related information used for recommending the product is created from the user related product information. However, the user who purchases (views) the product related to the product related information also purchases (views) this product. The user identifiers need not be specified for individual users, and the uniqueness among users can be maintained. All you have to do is Of course, the same person may purchase (browse) products between different stores, but especially with regard to purchases, it is unlikely that the same product will be purchased frequently between different stores. In this case, it may be regarded as another person.

  Next, the user related product information receiving unit 101 of the apparatus 1 receives the user related product information (step S5), and temporarily stores the information in a storage unit (not shown).

  Next, the product related information creation unit 103 of the apparatus 1 creates product related information from the user related product information temporarily stored (step S6). Inter-product related information represents information that associates products based on user behavior, and a user who purchases (views) a product purchases the relationship between products that the user also purchases (views) this product. It is created by associating products with each other based on the action history information purchased (viewed) on the Internet. For example, from the information that the user TENPO2A has purchased the products A, B, and G, “the user who purchased the product A (B) has purchased the product B (A)”, “purchased the product A (G) The user who has purchased the product G (A) ”and“ the user who purchased the product B (G) has purchased the product G (B) ”are obtained.

  A process in which the inter-product related information creating unit 103 creates the inter-product related information from the user-related product information will be described with reference to FIGS. In fact, as the user-related product information, even if the product is the same, a product identifier that uniquely represents a product is used to avoid recognizing that the product is different if the product name assigned to each store is different. The product related information is created by using the product name (A, B, etc.) instead of the product identification information for convenience of explanation.

  FIG. 4 shows user-related product information transmitted from the store apparatus 2 and the store apparatus 3 to the present apparatus 1, respectively. FIG. 4 (1) is user-related product information 213A transmitted from the store device 2 to the present device 1, and is information that a user whose user identifier is TENPO2A has purchased products A, B, and G. FIG. 4B is user-related product information 213B transmitted from the store apparatus 2 to the present apparatus 1, and is information that a user whose user identifier is TENPO3B has purchased the products B, Q, and H.

  The inter-product related information creating unit 103 tabulates and organizes the user-related product information transmitted from each of the store apparatuses 2 to N to create an association between the products. Specifically, when creating an association between products for products A, B, and G associated with TENPO2A, first select a reference product from A, B, and G, and then select a reference product. The products other than those are associated as related products and stored in the related information storage unit 111.

  FIG. 5A is a conceptual diagram of inter-product related information in which A is selected as the reference product and B and G are associated as related products. This indicates that “the user who purchased the product A has purchased the product B” and “the user who has purchased the product A has purchased the product G”.

  Similarly, as shown in FIGS. 5 (2) and 5 (3), inter-product related information when B and G are respectively selected as reference products is also created. The above is inter-product related information created from the user-related product information 213A.

  Next, the inter-product related information created from the user-related product information 213B will be described. Basically, it is not different from the creation processing from the user-related product information 213A described above. However, for example, when B is selected as the reference product, an entry for B already exists as shown in FIG. You just add to related information between goods. A conceptual diagram of the processing in that case is shown in FIG. In FIG. 6, the product related information when the reference product obtained from the user related product information 213A and 213B is the product B is merged.

  The inter-product related information created in this way represents the inter-product graph as shown in the conceptual diagram of FIG. 7 when the related products are regarded as the reference products and sequentially connected. Inter-product graphs are easy to understand intuitively when calculating the shortest distance between products and presenting the relationship between products to the user. May be.

  In addition, the data amount of the related information between products increases as the number of user-related product information periodically transmitted from each store apparatus 2 to N increases, and the amount of data that cannot be collected by only one store Needless to say, you can create spectacular product-related information using. In this invention, the useful effect that the information collected from each store can be used when recommending goods for each store as described later is obtained.

[2-1. (Send recommendation information)
Next, a process until a product is recommended to a user using inter-product related information will be described.

  The user terminal T1 makes a browsing request to the store apparatus 2 of the store that operates the shopping site in order to access the shopping site on the Internet (step S7). For example, in this case, it is assumed that the user operating the user terminal T1 is interested in the product B and accesses the detailed explanation page of the product.

  Next, the merchandise information transmission means 207 of the store apparatus 2 transmits the merchandise information posted on the page requested by the user terminal T1 to the apparatus 1 (step S8). The product information is preferably a product identifier. In the present embodiment, the store device 2 obtains a product identifier stored in association with the product B by referring to a product database (not shown), and transmits the product identifier to the device 1.

  Next, the product information receiving means 105 of the apparatus 1 receives the product information of the product B (step S9).

  Next, the recommended information extracting unit 107 of the apparatus 1 extracts related product information corresponding to the product information received by the product information receiving unit 105 from the inter-product related information storage unit 111 as recommended information (step S9).

  Specifically, a user who is interested in the product B received by the present apparatus 1 as product information with reference to the inter-product related information storage unit 111 extracts recommended information of products that may be of interest to others. In this case, it can be seen from the related information between the products in FIG. 6 that the user who has purchased the product B has purchased other products A, G, Q, and H. G, Q, and H are extracted. Note that what is actually extracted is a product identifier corresponding to the related product.

  In this embodiment, all the related products stored in the inter-product related information for the product B are extracted as extraction criteria. However, the present invention is not limited to this. In addition, a predetermined number may be extracted in descending order of frequency. In addition, related products over a plurality of layers, such as related products when the related products are used as reference products, may be extracted as recommendation information.

  Next, the recommended information transmitting unit 109 transmits the recommended information extracted by the recommended information extracting unit 107 to the store apparatus 2 that has transmitted the product information (step S11).

  The recommendation information receiving unit 209 of the store apparatus 2 receives the recommendation information (step S12), and the page transmission unit 211 incorporates the recommendation information into the page on which the detailed information of the product B is described and transmits the page data to the user terminal T1. (Step S13). Here, the page transmission unit 211 obtains information necessary for recommending a product on a shopping site such as a product photo based on product information (product identifier) relating to a related product that is set as recommendation information from a product database (not shown). And generate a page.

  FIG. 8 shows an example of a page transmitted to the user. Detailed information 2111 of the product B and recommendation information 1071 which is a recommended product for the product B are incorporated. If the user wants to purchase the product B, the user can transition to a page for purchasing the product by clicking an add button to the shopping cart provided at the bottom of the detailed information 2111. An add button provided below the recommendation information 1071 has a similar function.

[3. effect〕
As described above, according to the present invention, even if a recommendation system is not introduced for each store, the present device 1 extracts recommended information instead of the store and transmits it to the store device. A recommendation function can be provided to the user without introducing a system. In addition, even if sufficient user-related product information is not collected at a certain store, it is possible to utilize recommendation information created based on user-related product information collected from a plurality of stores.

[4. Embodiment 2]
In the first embodiment, when merchandise information that is not handled in a store is transmitted from the apparatus 1 as recommendation information, the merchandise information cannot be used as recommendation information in the store. The second embodiment to be described below solves this problem.

[4-1. Embodiment in which only handled products are posted]
In the present embodiment, only the products handled in the store are posted as recommended information.

  Specifically, in the above-described embodiment, the recommendation information receiving unit 209 of the store apparatus 2 receives the recommendation information, and the page transmission unit 211 includes a page in which the recommendation information is incorporated into the page on which the detailed information of the product B is described. At the time of creation, the page transmission means 211 refers to the product database (not shown) for the product information set as recommendation information, and checks whether the product information is held in the product database. By having a recommendation information target product possession confirmation means that is used as recommendation information and not recommended information when there is no recommendation information, it is possible to display only the products handled in the store as recommendation information.

[4-2. Embodiments that include products other than those handled]
In the present embodiment, products other than the products handled at the store are also posted as recommended information.

  An outline of the operation procedure of the device 1, the store device 2, and the user terminal T1 in the present embodiment will be described with reference to the sequence diagram of FIG. Note that step numbers common to those in the sequence diagram of FIG. 2 represent the same processing, and thus description thereof will be omitted as appropriate.

  Characteristic processing in the present embodiment is user-related product information transmission processing in step S4A and page data transmission processing in step S13A.

  In step S4A, as shown in FIGS. 10 (1) and 10 (2), the user-related product information transmission unit 203 adds the user identifier and product information as user-related product information, and the store device further stores its own store. Information associated with the store information is transmitted to the apparatus 1. Here, the store information is not particularly limited as long as the store can be specified, and examples thereof include a store name and a URL of a shopping site top page operated by the store.

  FIG. 10 (1) shows user-related product information 2130A in the case where the name of the store that owns the store apparatus 2 is XX store. This is nothing but the fact that XX stores handle the products related to the products A, B, and G. Similarly, FIG. 10 (2) shows user-related product information 2130B when the name of the store that owns the store device 3 is xx store.

  Next, the product related information creation unit 103 creates product related information based on the user related product information including the store information transmitted in step S4A (steps S5 and S6). As shown, the store information is referred to as a handling store of related products, and the related information between products is created in a state including the handling store information.

  FIG. 12 is a conceptual diagram when creating inter-product related information in which the reference product is the product B by merging the product related information when the reference product of the XX store and the XX store is the product B. . From this information, it is possible to grasp the store handling the product related to the product B.

  Next, when the store apparatus 2 makes an inquiry to the apparatus 1 in response to a browsing request from the user terminal T1 and receives recommendation information (steps S7 to S12), the page data transmission unit 211 selects a page based on the recommendation information. create. At this time, the store apparatus 2 of the present embodiment refers to a product database (not shown) among related products, and has a confirmation means for confirming whether or not the product information is held in the product database. Based on the page data, the page data transmission unit 211 creates a page. Specifically, for products that have the product information, create a page that incorporates recommendation information as recommendation information in the same way as the process described above, and refer to the product database for related products that are not held Is configured to incorporate recommended information with a link on the page so that the user can be guided to the shopping site of the store handling the product based on the store information included in the recommended information.

  As a method for generating the link, when the page data transmission unit 211 creates a page, for example, a product search is performed in the shopping site of the handling store based on the information of the related product and the handling store, and the URL of the corresponding page And an image, etc. are acquired, and a URL is linked to the image and incorporated into the page as recommendation information.

  The motivation for listing the products handled by other companies as recommendation information is to measure conversions such as the user's purchase behavior on the Internet induced by the link, taking a profit structure like so-called affiliate advertisements as an example. A business model such as charging from a handling store to a guide store can be used.

[5. Other Embodiments]
In the case of generating a page incorporating recommendation information in the above-described first and second embodiments, when acquiring information related to product information as recommendation information from the product database, the stock status of the product is also acquired, and there is no stock A process may be performed such that the information is not recommended information.

  In addition, when the device 1 transmits handling store information as recommendation information to each store device, the same product may include a plurality of handling stores, which are transmitted from the store device to the device 1. A predetermined number of stores from the top where the amount of information related to the user-related product information to be transmitted is large may be included in the recommended information as handling stores.

  Further, the present invention can be considered as an ASP service using the apparatus 1 as a recommendation engine, and stores using the service developed by the apparatus 1 are not necessarily limited to stores providing user-related product information to the apparatus 1. For example, the use of the service may be released to stores that do not provide user-related product information to the apparatus 1.

  Moreover, said each embodiment is only an illustration and this invention includes what is illustrated below and other embodiment other than that. For example, in the present invention, elements such as each means may be realized not only by an arithmetic control unit of a computer but also by an electronic circuit based on wired logic or the like, or a non-Neumann type information processing mechanism that will appear in the future. Further, each configuration diagram, data diagram, sequence diagram, and the like are merely examples, and the presence / absence of each element, its order, specific contents, and the like can be changed as appropriate.

  For example, the device configuration in FIG. 1 is merely an example, and the actual system is realized by a plurality of server devices such as individual devices (for example, storage means such as a database) realized by separate server devices. Alternatively, the configuration can be flexibly changed, for example, as a part of the system of the present invention including the user terminal T1. Also, some functions may be realized by calling an external platform or the like with an API (Application Program Interface) or network computing.

T1 User terminal device 1 Recommended information transmitting device 2 Store device 5 Arithmetic control unit 6 Storage device 7 Communication unit 101 User related product information receiving unit 103 Inter-product related information creating unit 105 Product information receiving unit 107 Recommended information extracting unit 109 Recommended information transmitting Means 111 Inter-product related information storage means 201 User related product information collection means 203 User related product information transmission means 205 Browsing request reception means 207 Product information transmission means 209 Recommendation information reception means 211 Page transmission means 213 User related product information storage means

Claims (4)

User-related product information receiving means for receiving user-related product information, which is information related to products based on user behavior transmitted from a plurality of store apparatuses;
Inter-product related information creating means for creating product-related information, which is information associated with products based on user behavior, used to recommend products from the received user-related product information;
Product information receiving means for receiving product information from the store device;
Recommended information extracting means for extracting related product information corresponding to the product information from the related information between products as recommended information;
A recommendation information transmitting apparatus, comprising: recommendation information transmitting means for transmitting the recommendation information extracted by the recommendation information extracting means to the store apparatus.   The recommended information transmitting apparatus according to claim 1, wherein the user-related product information is information in which at least a user identifier is associated with a product identifier corresponding to a product purchased or browsed by the user in the past.   The recommendation information transmitting apparatus according to claim 2, wherein the user-related product information is information in which store information is further associated with the product identifier. Computer
A user-related product information receiving step for receiving user-related product information that is information related to a product based on user behavior transmitted from a plurality of store apparatuses;
An inter-product related information creating step for creating inter-product related information, which is information associated with products based on user behavior, used to recommend products from the received user-related product information;
A product information receiving step for receiving product information from the store device;
A recommended information extracting step of extracting related product information corresponding to the product information as recommended information from the inter-product related information;
A recommended information transmitting method comprising: executing a recommended information transmitting step of transmitting the recommended information extracted in the recommended information extracting step to the store apparatus.

Images