JP6311052B1 - Extraction apparatus, extraction method, and extraction program - Google Patents

Abstract

An object of the present invention is to efficiently expand a distribution target user while maintaining a high content appeal effect. An extraction apparatus according to the present application includes a specifying unit and an extraction unit. The specifying unit specifies a related store that is a store related to the first store managed by the provider of the predetermined content. The extraction unit extracts a target user who is a candidate for a predetermined content providing destination based on the access information to the related store specified by the specifying unit. For example, the specifying unit specifies a related store based on a search result obtained from a query that outputs a first store or a product handled by the first store as a search result when input to a predetermined search engine. [Selection] Figure 1

Description

  The present invention relates to an extraction apparatus, an extraction method, and an extraction program.

  Conventionally, there is a technique called retargeting advertisement as one technique for distributing advertisements via the Internet. For example, such a technique displays advertisement content having a link to the predetermined website on the user terminal of the user who accesses the predetermined website, and prompts the user to access the predetermined website.

  As a technique related to advertisement distribution as described above, a technique for distributing advertisements to a user who visits a website similar to a website provided by an advertiser is known. In addition, a technique for distributing an advertisement based on information associated with a notification tag included in a web page is known.

JP, 2006-62370, A JP, 2006-177650, A

  However, there is room for further improvement in effective advertisement distribution to users. For example, in the conventional technology, advertisement distribution can be performed to a user who visited a website similar to the website provided by the advertiser or a user who visited a page equipped with a tag for notification. In some cases, effective advertisement distribution may not be possible. Note that such problems related to distribution are common not only to advertisement distribution but also to distribution of information content such as video content and product recommendations.

  The present application has been made in view of the above, and an object thereof is to provide an extraction device, an extraction method, and an extraction program that can efficiently expand a distribution target user while maintaining a high appeal effect of content. To do.

  The extraction device according to the present application is based on a specifying unit that specifies a related store that is a store related to a first store managed by a predetermined content provider, and access information to the related store specified by the specifying unit. And an extraction unit for extracting a target user who is a candidate for a destination of the predetermined content.

  According to one aspect of the embodiment, there is an effect that the distribution target user can be efficiently expanded while maintaining a high appeal effect of the content.

FIG. 1 is a diagram illustrating an example of an extraction process according to the embodiment. FIG. 2 is a diagram for explaining an example of the specifying process according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of the extraction system according to the embodiment. FIG. 4 is a diagram illustrating a configuration example of the extraction device according to the embodiment. FIG. 5 is a diagram illustrating an example of the advertisement information storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of a search result table according to the embodiment. FIG. 7 is a diagram illustrating an example of a relation table according to the embodiment. FIG. 8 is a diagram illustrating an example of the access information storage unit according to the embodiment. FIG. 9 is a diagram illustrating a configuration example of the web server according to the embodiment. FIG. 10 is a flowchart (1) illustrating a processing procedure according to the embodiment. FIG. 11 is a flowchart (2) illustrating a processing procedure according to the embodiment. FIG. 12 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the extraction device.

  Hereinafter, an embodiment (hereinafter referred to as “embodiment”) for carrying out an extraction apparatus, an extraction method, and an extraction program according to the present application will be described in detail with reference to the drawings. In addition, the extraction apparatus, the extraction method, and the extraction program which concern on this application are not limited by this embodiment. In addition, the embodiments can be appropriately combined within a range that does not contradict processing contents. In the following embodiments, the same portions are denoted by the same reference numerals, and redundant description is omitted.

[1. Example of extraction process)
First, an example of the extraction process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of an extraction process according to the embodiment. In FIG. 1, the extraction apparatus 100 according to the present application uses a process for identifying a related store, which is a store related to a store managed by a predetermined content provider, and based on access information to the related store, An example in which a process of extracting a user who is a candidate for a destination is performed will be described.

  In the embodiment, as an example of the predetermined content, an advertisement content (hereinafter simply referred to as “advertisement”) displayed on a web page or the like will be described as an example. In the embodiment, it is assumed that a predetermined content provider (that is, an advertiser) is an administrator of a store that opens a shopping mall operated on a network. In other words, the provider of the predetermined content desires to distribute the store advertisement managed by the predetermined content to the user. In the following description, a store managed by a predetermined content provider is a first store, a store managed by a party other than the predetermined content provider, and a store opened in the same shopping mall as the first store Is referred to as a second store.

  In the embodiment, it is assumed that a predetermined content provider desires to distribute an advertisement submitted by himself / herself as a retargeting advertisement to a user. The retargeting advertisement is an advertisement that is distributed to a user who has accessed the first store in the past, and since an advertisement that matches the interest of the user can be distributed, the advertising effect is generally considered high. However, since the retargeting advertisement is distributed based on the history of the user accessing the first store in the past, it cannot be distributed to the user who has no history of accessing the first store. For this reason, when the number of accesses to the first store is not sufficient, or when the first store has just opened in a shopping mall, it is difficult to deliver the retargeting advertisement as many as the provider desires. There is a case.

  Therefore, the extraction apparatus 100 according to the embodiment specifies a related store that is a store related to the first store, and based on access information to the related store, a user who is a candidate for a predetermined content provision destination (hereinafter, referred to as a “providing destination”) , Expressed as “target user”).

  For example, the extraction device 100 specifies a related store related to the first store from the second stores. The store associated with the first store in the same shopping mall is, in other words, a store competing with the first store, and it is presumed that the assortment of products and the like requested by the user as a customer is similar to each other. Although the extraction device 100 has no history of accessing the first store, the extraction device 100 can perform processing such as distributing the advertisement of the first store to the target user by extracting the target user who has accessed the related store. . In other words, according to the extraction device 100, a predetermined content provider can distribute his / her advertisement to a user who accesses a store competing with the first store. For this reason, the provider of the predetermined content can efficiently distribute an advertisement having the same effect as the retargeting advertisement. In addition, in this specification, a product is a concept including a wide range of objects of commercial transactions, and is a concept including services as well as products. Hereinafter, an example of the extraction process performed by the extraction apparatus 100 will be described along the flow with reference to FIG.

  The extraction device 100 illustrated in FIG. 1 is a server device that accepts advertisement submissions from the administrator of the first store and distributes the accepted advertisements to the user. In addition, as will be described below, the extraction apparatus 100 identifies a related store of the first store, and extracts users who are candidates for advertisement distribution destinations based on access information to the related store.

  The shopping mall AAA is an example of a shopping mall that is operated on a network. The store B01 and the store B02 are examples of stores that have opened in the shopping mall AAA. In the example of FIG. 1, it is assumed that the store B01 is the first store and the store B02 is the second store. In the following description, an action executed by a store manager or the like may be read as the store executes. For example, the manager of the store B01 may state that an advertisement is submitted as “store B01 submits an advertisement”.

The user terminal 10 ₁ and 10 ₂ shown in FIG. 1 is an information processing terminal that is utilized by the user. In the example of FIG. 1, the user terminal 10 ₁ is utilized by the user U01, the user terminal 10 ₂ is used by the user U02. The user terminal 10 ₁ and 10 ₂ is, for example, a smartphone or a tablet terminal. User U01 or user U02 accesses the Web server 30 (see FIG. 3) via the user terminal 10 ₁ and 10 _2, (in the example of FIG. 1, the shopping mall AAA) web site provided by the web server 30 Use. In the following, when it is not necessary to distinguish between the user terminal 10 ₁ and the user terminal 10 _2, collectively referred to as "user terminal 10". In addition, when it is not necessary to distinguish between the user U01 and the user U02, they are simply expressed as “user”. Moreover, below, the user terminal 10 and the user who uses the user terminal 10 may be identified. For example, "sends the content to the user U01", in fact, it may mean that the "transmitting the content to the user terminal 10 ₁ user U01 to use". Although illustration in FIG. 1 is omitted, the user U01 and the user U02 do not indicate a single user but may indicate the presence of a plurality of users.

  In the example illustrated in FIG. 1, first, the store B01 that is the first store submits a retargeting advertisement to the extraction device 100 (step S11). For example, the store B01 submits an advertisement for promoting its own store, and specifies the extraction apparatus 100 to distribute the advertisement as a retargeting advertisement.

Thereafter, it is assumed that the user U01 who uses the shopping mall AAA executes processing for searching for a product or a store in the shopping mall AAA (step S12). For example, the user U01 via the user terminal 10 _1, enters a query into a search engine for searching a product or store in the shopping mall AAA.

  Then, the user U01 accesses the store B01 after the search action (step S13). At this time, the extraction device 100 acquires information related to the search performed by the user U01 (step S14). Specifically, the extraction device 100 acquires the search behavior of the user U01 performed in the shopping mall AAA, access information indicating that the user U01 has accessed the store B01 after the search, and the like. Then, the extraction device 100 specifies the related store of the store B01 based on the search result (step S15). Details of the specific processing will be described later.

  In the example of FIG. 1, it is assumed that the extraction apparatus 100 specifies the store B02 as the related store of the store B01. The extraction device 100 appropriately stores the relationship between the specified stores in the store related information storage unit 122 (step S16). For example, since the related store of the store B01 is the store B02, the extraction apparatus 100 stores the store B01 and the store B02 in association with each other in the store related information storage unit 122.

  Thereafter, it is assumed that the user U02 has accessed the store B02, which is a related store of the store B01 (step S17). The extraction device 100 acquires access information of the user U02 (step S18).

Thereafter, extraction device 100, such as when the user terminal 10 ₂ displays a page with inventory, to obtain the effect that the advertisement distribution opportunity has occurred in the user terminal 10 _2. At this time, the extraction apparatus 100 extracts the user U02 as a target user related to the store B01 based on the history of the user U02 accessing the store B02 that is a related store of the store B01. Then, the extraction device 100 distributes the retargeting advertisement submitted by the store B01 to the extracted user U02 (step S19).

  As described above, the extraction device 100 according to the embodiment specifies the store B02 as the related store related to the first store, and the distribution destination candidate of the advertisement of the first store based on the access information to the store B02. Target user to be extracted.

  That is, the extraction device 100 according to the embodiment distributes the retargeting advertisement of the store B01 by using the access information to the store B02 that is the related store even when the access to the store B01 is not sufficient. A target user as a delivery destination can be extracted. In other words, the extraction apparatus 100 can expand the delivery destination of the retargeting advertisement in the store B01 to a user who does not actually have an access history to the store B01, such as the user U02. Further, since the store B02 is highly likely to be a store competing with the store B01, it is assumed that the interest of the user as a customer is also close to each other. For this reason, it is estimated that the advertisement of the store B01 exerts a high appealing effect on the user who is a customer of the store B02. In this way, the extraction device 100 can expand the users who are the distribution destinations while maintaining a high advertising appeal effect.

  FIG. 1 shows an example in which the extraction device 100 acquires the action history (access information) that the user U01 accessed the store in step S13. The extraction device 100 may acquire the access information and the like using various methods. For example, the extraction apparatus 100 may acquire user behavior information using a notification function realized by a web beacon or the like.

  That is, the content (web page) in the shopping mall AAA may be embedded with a function for notifying information about the user (hereinafter referred to as “user information”) realized by a web beacon or the like. For example, the web beacon has a function of allowing the user terminal 10 that has accessed the web page to access a transparent image or a very small image (sometimes referred to as “clear GIF”) stored in the extraction device 100. Thereby, the extraction device 100 can receive and acquire user information from the user terminal 10. For example, the extraction device 100 can use the function realized by the web beacon to allow the user U01 to access the first store on the user terminal 10, browse the product, purchase the product, Clicked information can be received.

  By the way, as described above, in order to expand the users as distribution destinations while maintaining a high advertising appeal effect, it is desirable that the extraction device 100 specifies the related store with high accuracy. In this regard, details of the specific process performed by the extraction apparatus 100 will be described with reference to FIG.

FIG. 2 is a diagram for explaining an example of the specifying process according to the embodiment. FIG. 2 shows a situation in which process the goods to find in the shopping mall AAA in the user terminal 10 ₁ is being performed. Specifically, in FIG. 2, the search page 60 displayed on the user terminal 10 _1, the search results 62 when the user U01 has entered the query "product A01" in the search window 61 the user terminal 10 ₁ is displayed An example is shown. The user terminal 10 ₁ is retrieved as a result 62, and displays or links 64 to the store B02, and links 66 to the store B03, the link 68 to the store B01.

In FIG. 2, it is assumed that the user U01 has selected the store B01 from the displayed stores. Specifically, the user U01 touches the link 68 using the finger 80. In this case, the user terminal 10 _1, shifts the screen to the sales page of the goods and the like A01 in the shopping mall AAA store B01. That is, the user U01 is a user who has flowed into the store B01 when a search is performed using the query “product A01”.

  In this way, the extraction device 100 acquires a query that triggered the flow into the first store (step S21). The extraction apparatus 100 acquires a plurality of queries that have triggered the flow into the first store by repeating the process of step S21.

  Here, the extraction apparatus 100 performs a process of counting the second stores searched by inputting the acquired query to the search engine (step S22). Specifically, the extraction device 100 acquires search results searched by a query by sequentially calling a search API (Application Programming Interface) with the acquired query. In this case, as a search result, a plurality of second stores belonging to the shopping mall AAA are searched together with the first store. For example, in the case where the query is a product name, among the second stores belonging to the shopping mall AAA, the store handles the product corresponding to the query, and the store with higher sales or the store with higher sales is ranked higher. Expected to be searched. Then, the extraction apparatus 100 extracts the second store included in the search results up to a predetermined rank (for example, 20th).

  For example, the extraction apparatus 100 extracts the second store searched for each query as shown in Table 70 shown in FIG. For example, in the table 70 illustrated in FIG. 2, the query “product A01” indicates that “B02”, “B03”, and “B04” are searched as the second store. The query “product A02” indicates that “B02”, “B05”, and “B07” are searched as the second store.

  Since the query “product A01” and the query “product A02” are queries that triggered the user U01 to flow into the store B01, the second store searched by these queries is similar to the first store. It can be said that it is a store that deals with the store, ie, a competitive store. And the extraction apparatus 100 extracts the 2nd store searched using a some query, and counts the number extracted.

  Then, the extraction device 100 specifies the related store of the first store based on the counted result (step S23). Specifically, the extraction device 100 identifies a predetermined number (for example, 20) of second stores as related stores in descending order of the counted number. Thereby, the extraction apparatus 100 can accurately extract a store that is assumed to compete with the first store, and specify it as a related store. In the example of FIG. 2, as illustrated in Table 72, the extraction apparatus 100 identifies the store “B02”, the store “B03”, and the store “B05” among the second stores as the related stores of the first store. To do.

  Note that the specifying process shown in FIG. 2 is an example, and the extracting apparatus 100 may specify the related store by various methods. For example, the extraction device 100 may accept input of definition data between related stores in advance from the administrator of the extraction device 100 or the administrator of the shopping mall AAA, and specify the related store based on the definition data. . Alternatively, the extraction device 100 acquires a product list of a store belonging to the shopping mall AAA, and when the product handled by the first store is purchased from the user at the second store, the second store is retrieved. You may specify as a related store.

  Note that the query extracted by the extraction device 100 described above is an example, and the extraction device 100 is not only a product name but any query that triggers the user U01 to flow into the first store. May be obtained.

  Hereinafter, the configuration of the extraction apparatus 100 that performs the processing described in FIG. 1 and the extraction system 1 including the extraction apparatus 100 will be described in detail.

[2. (Extraction system configuration)
Next, the configuration of the extraction system 1 including the extraction device 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram illustrating a configuration example of the extraction system 1 according to the embodiment. As illustrated in FIG. 3, the extraction system 1 according to the embodiment includes a user terminal 10, a web server 30, and an extraction device 100. These various apparatuses are communicably connected via a network N (for example, the Internet) in a wired or wireless manner. Note that the extraction system 1 illustrated in FIG. 3 may include a plurality of user terminals 10 and a plurality of web servers 30.

  The user terminal 10 is, for example, an information processing apparatus such as a smartphone, a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), or a wearable device. It is. The user terminal 10 acquires the web page from the website provided from the web server 30 by accessing the web server 30 according to the operation by the user. Then, the user terminal 10 displays the acquired web page on a display device (for example, a liquid crystal display).

  The web server 30 is a server device that provides various services when accessed from the user terminal 10. In the embodiment, the web server 30 provides a web page related to a shopping site such as a shopping mall as a service. In addition to the shopping site, the web server 30 includes a search service site, an auction site, a news site, a weather forecast site, a finance (stock price) site, a route search site, a map providing site, a travel site, a restaurant introduction site, a web Various web pages related to blogs may be provided.

  Note that the web page distributed by the web server 30 may include a recommendation frame or an advertisement frame for displaying a recommendation or an advertisement. The web page including the recommendation frame and the advertisement frame includes an acquisition command for acquiring a recommendation and an advertisement displayed in the frame. For example, in an HTML (HyperText Markup Language) file that forms a web page, the URL of the extraction device 100 is described as an acquisition command. In this case, the user terminal 10 receives a recommendation or an advertisement from the extraction device 100 by accessing a URL described in an HTML file or the like.

  Further, the web server 30 may acquire a list of products handled by the store, identification information for identifying each product, and the like from each store that opens a shopping site or the like. The web server 30 acquires such information and holds it in a predetermined database. For example, the extraction device 100 can refer to store information indicating what products each store handles by acquiring these pieces of information held by the web server 30.

  The extraction apparatus 100 identifies a related store that is a store related to the first store managed by the provider of the predetermined content, and based on access information to the specified related store, a candidate for a predetermined content providing destination It is a server device that extracts the target user.

  Note that the extraction device 100 identifies the user terminal 10 and identifies the user terminal 10 that distributes the advertisement when distributing the advertisement. For example, the user can be identified by including user identification information in a cookie exchanged between the web browser of the user terminal 10 and the extraction device 100 (or the web server 30). However, the method for identifying the user is not limited to the above. For example, a dedicated program may be set in the user terminal 10 and user identification information may be transmitted to the extraction device 100 from the dedicated program. Such a program is realized as an application for a smartphone, for example.

[3. (Extractor configuration)
Next, the configuration of the extraction apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 4 is a diagram illustrating a configuration example of the extraction device 100 according to the embodiment. As illustrated in FIG. 4, the extraction device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The extraction device 100 includes an input unit (for example, a keyboard and a mouse) that receives various operations from an administrator who uses the extraction device 100, and a display unit (for example, a liquid crystal display) for displaying various types of information. You may have.

(About the communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to the network N in a wired or wireless manner, and transmits / receives information to / from the user terminal 10 and the web server 30 via the network N.

(About the storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 includes an advertisement information storage unit 121, a store related information storage unit 122, and an access information storage unit 125.

(Regarding the advertisement information storage unit 121)
The advertisement information storage unit 121 stores information related to advertisements. FIG. 5 shows an example of the advertisement information storage unit 121 according to the embodiment. FIG. 5 is a diagram illustrating an example of the advertisement information storage unit 121 according to the embodiment. In the example illustrated in FIG. 5, the advertisement information storage unit 121 includes “advertiser store ID (first store ID)”, “advertisement ID”, “distribution condition”, “number of impressions”, “number of guaranteed impressions”, “ “Distribution period”.

  “Advertiser store ID (first store ID)” indicates identification information for identifying a store that is an advertiser. “Advertisement ID” indicates identification information for identifying an advertisement. In this specification, the identification information as shown in FIG. 5 is common to the reference numerals used in the description. For example, the store identified by the advertiser store ID “B01” indicates “store B01”. The advertisement identified by the advertisement ID “C01” may be referred to as “advertisement C01”.

  “Distribution condition” indicates the distribution condition of the advertisement. FIG. 5 shows an example in which conceptual information such as “E01” is stored in the distribution condition. Actually, the item of the distribution condition includes whether the advertisement is a retargeting advertisement, Information such as designation of user attribute information (age, gender, etc.) extracted as a delivery destination, designation of contents of a medium (web page) having an advertising space as a delivery destination, and the like is stored.

  The “number of impressions” indicates the number of times that an advertisement has been distributed (displayed on the user terminal 10) at the present time. The “number of guaranteed impressions” indicates a number guaranteed as the number of times an advertisement submitted by the advertiser is delivered. For example, the advertiser designates the guaranteed number of impressions and submits the advertisement to the extraction apparatus 100. The extraction device 100 distributes the advertisement to the user terminal 10 so as to achieve the number of impressions specified by the advertiser.

  “Distribution period” indicates a period during which an advertisement is distributed. For example, for the advertisement for which the distribution period is set, the extraction device 100 distributes the guaranteed number of impressions before the distribution period elapses.

  That is, the example shown in FIG. 5 indicates that the store B01 whose advertiser store ID (first store ID) is “B01” has submitted the advertisement C01 identified by the advertisement ID “C01”. Yes. Further, the distribution condition of the advertisement C01 is “E01”, the current number of impressions is “5000” times, the guaranteed number of impressions designated by the store B01 as the advertiser is “20000” times, and the distribution period is “ April 1, 2017 to June 30, 2017 ".

  Although illustration in FIG. 5 is omitted, the advertisement information storage unit 121 may further store, for example, an index value such as CTR (Click Through Rate) indicating the advertisement effect of the advertisement C01.

(About the store related information storage unit 122)
The store related information storage unit 122 stores information related to store relevance. The store related information storage unit 122 according to the embodiment includes a search result table 123 and a related table 124 as data tables. Hereinafter, each data table will be described in order.

(Regarding the search result table 123)
The search result table 123 stores a query that triggers the user to flow into the first store, information about the second store searched by the query, and the like. FIG. 6 shows an example of the search result table 123 according to the embodiment. FIG. 6 is a diagram illustrating an example of the search result table 123 according to the embodiment. In the example illustrated in FIG. 6, the search result table 123 includes items such as “first store ID”, “search information”, and “sales information”. “Search information” has small items such as “inflow query” and “second store ID”. The “sales information” has small items such as “sales ranking” and “sales ranking of the first store”.

  The “first store ID” corresponds to the advertiser store ID shown in FIG. “Search information” indicates result information obtained by performing a search using a query that triggered the user to enter the first store. The “inflow query” indicates a query that triggers the user to flow into the first store. “Second store ID” is identification information for identifying the second store. Note that the second store ID shown in FIG. 5 indicates identification information of the second store displayed as a search result when a search is performed by an inflow query.

  “Sales information” indicates information related to sales of the product in the shopping mall to which the first store and the second store belong when the query is a product. “Sales rank” indicates the rank of sales between stores searched by the inflow query. “Sales rank of the first store” indicates the sales rank of the first store in the store searched by the inflow query. When the query is not a product, the sales information may be read as “order of search results”. Further, the extraction device 100 acquires sales information in the shopping mall from, for example, the web server 30.

  That is, in the example illustrated in FIG. 6, the inflow query of the store B01 that is the first store indicates, for example, “product A01” or “product A02”. Further, when a search is performed with “product A01”, the second store displayed in the search result is, for example, the second store ID “B02”, “B03”, “B04”, “B07”, and the like. It is shown that. Among the searched second stores, the store having the first sales rank in the product A01 is the store B02, the store having the second sales rank is the store B03, and the store having the fourth sales rank. Indicates that the store is the store B04 and the store with the sales rank of 5 is the store B07. Further, the store B01 which is the first store indicates that the sales rank in the product A01 is “3rd place”.

(Regarding related table 124)
The association table 124 stores information related to the association store. FIG. 7 shows an example of the association table 124 according to the embodiment. FIG. 7 is a diagram illustrating an example of the association table 124 according to the embodiment. In the example illustrated in FIG. 7, the related table 124 includes items such as “first store ID”, “second store information”, and “related store”. The “second store information” has small items such as “search result information”, “second store ID”, and “appearance count”.

  The “first store ID” corresponds to the same item shown in FIG. “Second store information” indicates information related to the second store. “Search result information” indicates information on a search result performed using the inflow query of the first store. FIG. 7 shows an example in which conceptual information such as “F01” is stored in the search result information, but in actuality, the search result information items include keywords corresponding to the inflow query and the number of inflow queries. In addition, statistical information such as the date and time information on which the search is performed is stored. The search result information may be updated as needed when a new inflow query is acquired.

  The “second store ID” corresponds to the same item shown in FIG. “Number of appearances” indicates the number of times a second store has appeared as a result of a search performed by a plurality of inflow queries. In addition, when the same store appears twice or more in the search result by one inflow query, the extraction apparatus 100 may count the stores that have appeared multiple times, or may count the number of appearances as they are. May be.

  “Related store” indicates identification information of a store specified as a store related to the first store among the second stores. The related store is determined, for example, by specifying a predetermined number (for example, 20) of second stores in the order of appearance frequency.

  That is, in the example illustrated in FIG. 7, the search result information associated with the first store B01 is “F01”, and the second store that appears as the search result in the search result information is, for example, “B02”. ”,“ B03 ”,“ B04 ”,“ B05 ”,“ B06 ”,“ B07 ”,“ B08 ”, and the like. Further, for example, the number of times “B02” has appeared as a search result is “165”, the number of times “B03” has appeared is “135”, and the like. The second store specified as the related store related to the store B01 as the first store is, for example, “B02”, “B03”, “B05”, “B08”, “B07”, “B12”, “B16”, and the like are indicated.

(Regarding the access information storage unit 125)
The access information storage unit 125 stores various types of information related to the user, including user access information. FIG. 8 illustrates an example of the access information storage unit 125 according to the embodiment. FIG. 8 is a diagram illustrating an example of the access information storage unit 125 according to the embodiment. In the example illustrated in FIG. 8, the access information storage unit 125 includes items such as “user ID”, “attribute information”, “access information”, “conversion information”, and “reaction information”.

  “User ID” indicates identification information for identifying the user or the user terminal 10. “Attribute information” indicates attribute information such as the gender and age of the user. “Access information” indicates information related to access such as the number of times the user accesses the store and the date and time. “Conversion information” indicates information related to conversion such as the number of times a user has converted in the store (for example, purchase of a product, etc.) and the date and time. “Reaction information” indicates information related to the reaction to the advertisement, such as the number and ratio of the user clicking the advertisement, the time and the number of times the user browsed the advertisement, and the like.

  In the example shown in FIG. 8, the information stored in “attribute information”, “access information”, “conversion information”, and “reaction information” is “G01”, “H01”, “J01”, “K01”. In fact, specific information is stored in each item. For example, the attribute information stores attribute information such as the user's sex, age, residence, family structure, and annual income. The reaction information stores information that statistics the number and frequency of clicking on the distributed advertisement, the number and frequency of conversion with respect to the advertisement, and the like. Note that the extraction device 100 may represent the reaction information with a predetermined score. For example, the extraction device 100 may calculate a score related to reaction information in accordance with a click on an advertisement, the number of conversions, a rate, and the like. Then, the extraction apparatus 100 may perform an adjustment process such as preferentially delivering a predetermined product to a user who easily reacts to an advertisement. Moreover, reaction information may be produced | generated for every store. For example, in the extraction process, the extraction apparatus 100 may make adjustments such that the store is easily advertised to users who frequently react to advertisements in a predetermined store.

  That is, in the example shown in FIG. 8, the user U01 identified by the user ID “U01” has attribute information “G01”, access information “H01”, conversion information “J01”, It indicates that the information is “K01”.

(About the control unit 130)
The control unit 130 is a controller, for example, various programs (an example of an extraction program) stored in a storage device inside the extraction device 100 by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. This is realized by executing the RAM as a work area. The control unit 130 is a controller, and is realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

  As shown in FIG. 4, the control unit 130 includes a reception unit 131, an acquisition unit 132, a specification unit 133, a reception unit 134, an extraction unit 135, and a distribution unit 136. Information described below Implement or execute a processing function or action. Note that the internal configuration of the control unit 130 is not limited to the configuration illustrated in FIG. 4, and may be another configuration as long as the information processing described below is performed. In addition, the connection relationship between the processing units included in the control unit 130 is not limited to the connection relationship illustrated in FIG. 4, and may be another connection relationship.

(About the reception unit 131)
The accepting unit 131 accepts submission of predetermined content. Specifically, the accepting unit 131 accepts advertisement submission from a store where advertisement delivery is desired. The receiving unit 131 may receive a delivery condition such as delivering the advertisement as a retargeting advertisement when the advertisement is submitted.

  In addition, the accepting unit 131 may accept designation of the number of distributions for distributing advertisements to the user when the advertisement is submitted. That is, the reception unit 131 receives a designation of the number guaranteed as the number of impressions from the advertiser.

  The accepting unit 131 may accept designation of a delivery period for delivering the advertisement to the user when the advertisement is submitted. In addition, the reception unit 131 may receive so-called targeting information such as attribute information of a user who is a distribution destination as a distribution condition.

  The accepting unit 131 stores information regarding the accepted advertisement in the storage unit 120 as appropriate. For example, the reception unit 131 stores information regarding the received advertisement in the advertisement information storage unit 121.

(About the acquisition unit 132)
The acquisition unit 132 acquires various types of information. For example, the acquisition unit 132 acquires a query related to a first store or a product handled by the first store. Specifically, the acquisition unit 132 acquires a query that, when input to a predetermined search engine, causes the first store or a product handled by the first store to be output as a search result.

  In addition, the acquisition unit 132 may acquire a query that triggers the user to access the first store. In other words, the acquisition unit 132 acquires the inflow query that triggered the user to flow into the first store.

  Moreover, the acquisition part 132 may acquire the information regarding the user who uses a shopping mall. For example, the acquisition unit 132 acquires information that a user accesses an arbitrary store in a shopping mall. Moreover, the acquisition part 132 may acquire the user's action log in a shopping mall. Specifically, the acquisition unit 132 may acquire history information indicating that the user has converted in the store.

  The acquisition unit 132 may acquire, for example, at least one of browsing a predetermined product by a user, setting a purchase candidate (registration in a so-called wish list), or purchase as a conversion history.

  Moreover, the acquisition part 132 may acquire a user's reaction with respect to an advertisement, when an advertisement is delivered to the user. For example, the acquisition unit 132 acquires at least one of the number or rate at which the advertisement is selected (clicked or touched) from the user or the number or rate at which conversion related to the advertisement is achieved as a user reaction to the advertisement. To do. The conversion related to the advertisement indicates, for example, that the store to which the advertisement is linked is accessed, that the user actually purchases the advertised product, and the like. Moreover, the acquisition part 132 may acquire the index value which shows appeal effects, such as CTR (Click Through Rate) and CVR (Conversion Rate).

  The acquisition unit 132 may acquire information related to the store. For example, the acquisition unit 132 acquires a list of products handled by the store, identification information for identifying each product, and the like from the web server 30.

  Further, the acquisition unit 132 may appropriately acquire information stored in the storage unit 120. Moreover, the acquisition part 132 may store the acquired information in the memory | storage part 120 suitably. For example, the acquisition unit 132 stores information about the acquired query in the store related information storage unit 122.

(About the specific part 133)
The specifying unit 133 specifies a related store that is a store related to the first store managed by a predetermined content provider. Specifically, the specifying unit 133 specifies a related store related to the first store that is the advertiser.

  For example, the specifying unit 133 is a store related to the query acquired by the acquiring unit 132 and specifies a related store from stores other than the first store. Specifically, the specifying unit 133 specifies the related store based on the search result obtained when the query acquired by the acquiring unit 132 is input to a predetermined search engine. As an example, the specifying unit 133 specifies a related store based on a search result obtained when a query that triggers a user to access the first store is input to a predetermined search engine.

  More specifically, the specifying unit 133 is a store or product that is output as a search result together with the first store or the first store when a query is input to a predetermined search engine, and is other than the first store The related store is specified from the second store based on the second store or the product handled by the second store. For example, the specifying unit 133 performs search processing using a plurality of queries, and specifies a second store having a large number counted as a search result as a related store.

  The specifying unit 133 may count the store or the product output as the search result by any method. For example, the specifying unit 133 may extract a store or a product included in text data (snippet or the like) output as a search result, specify a store name or a product name, and count the specified number. Further, the specifying unit 133 may specify a store as a link destination based on the link information output as a search result, and count the specified number.

  Further, the specifying unit 133 may specify, as an associated store, a second store that handles products whose sales order is equal to or higher than a predetermined rank among the products searched by the query. In other words, the specifying unit 133 may perform adjustment so that a store that is output higher in the search result is specified as a related store. Specifically, the specifying unit 133 may specify a related store by using a store that is output as a search result in a higher rank (for example, within 20th rank). Thereby, the specifying unit 133 can specify the second store having higher competitiveness as the related store.

  The specifying unit 133 does not necessarily need to specify the related store using only the search result. For example, the specifying unit 133 may specify the related store based on the user action history. Specifically, the specifying unit 133 determines the second store based on the history information that the user having the history of conversion in the first store has converted in the store (second store) other than the first store. May be identified as a related store.

  That is, the identification unit 133 determines that the user having a history of conversion in the first store has also converted in the second store, so that the second store is in a competitive relationship with the first store, The second store is specified as the related store. For example, the specifying unit 133 may specify the second store as a related store based on, for example, a determination that the number of times the user has reached conversion in the second store exceeds a predetermined number.

(Receiver 134)
The receiving unit 134 receives an advertisement distribution request. For example, the receiving unit 134 receives a request related to the distribution of an advertisement displayed in an advertisement frame included in the web page, which is a request transmitted from the user terminal 10 that displays the web page. In other words, the receiving unit 134 receives information indicating that an advertisement distribution opportunity has occurred in the user terminal 10. The receiving unit 134 sends the received distribution request to the extracting unit 135.

  The receiving unit 134 may receive information for identifying the user terminal 10 as well as receiving a distribution request transmitted from the user terminal 10. For example, the reception unit 134 receives a cookie transmitted from the user terminal 10.

(About the extraction unit 135)
Based on the access information to the related store specified by the specifying unit 133, the extracting unit 135 extracts a target user who is a candidate for a predetermined content providing destination. For example, when the receiving unit 134 receives information indicating that an advertisement distribution opportunity has occurred, the extraction unit 135 extracts the user as a target user based on the access information of the user who generated the advertisement distribution opportunity. Note that the extraction unit 135 may extract the target user in advance as a distribution destination of the advertisement in the first store before the reception unit 134 receives that the advertisement distribution opportunity has occurred. In this case, the extraction unit 135 may control the advertisement to be distributed to the target user when an advertisement distribution opportunity occurs in the extracted target user.

  For example, the extraction unit 135 may extract the target user based on the number of times the user accesses the related store, the ratio of accessing the related store among the accesses in the shopping mall, or the like. Specifically, the extraction unit 135 preferentially extracts a user as a target user as the number of times or the ratio of accessing the related store is higher.

  Note that the extraction unit 135 may extract the target user based not only on the presence / absence of the history of accessing the related store but also on various information. For example, the extraction unit 135 may extract the target user based on history information indicating that the user has converted in the related store. Specifically, the extraction unit 135 may preferentially extract a user as a target user as the number of times or the ratio of conversion in the related store is higher. It can be said that a user who has a large number of conversions or a ratio in the related store, that is, a user who frequently makes a purchase or the like at a store competing for the first store. The extraction unit 135 preferentially extracts such a user as a target user, thereby increasing the chances that the advertisement of the first store is distributed to the user. As a result, the extraction unit 135 can attract users who are customers from the competing second store to the first store.

(About distribution unit 136)
The distribution unit 136 distributes various information. For example, the distribution unit 136 distributes the advertisement received by the reception unit 131 to the target user extracted by the extraction unit 135. The distribution unit 136 may further distribute the advertisement to the matched users by matching the target user extracted by the extraction unit 135 with the distribution conditions set for each advertisement. For example, the distribution unit 136 may distribute the advertisement by selecting a user according to a condition such as sex or age specified by the advertiser from the target users.

  Further, the distribution unit 136 may determine whether or not to distribute the advertisement to the target user based on the current situation such as the remaining number of advertisements in the advertisement distribution. Specifically, the distribution unit 136 distributes the advertisement to the target user when the remaining number of distributions specified by the advertiser exceeds a predetermined number, and the remaining number of specified distributions. May be distributed to a user who has a history of accessing the first store. In other words, the distribution unit 136 expands the distribution target when the remaining number of distributions is a predetermined number or more (for example, half or more of the specified number of distributions), and advertises the target user. To deliver. On the other hand, when the remaining number of distributions is equal to or less than the predetermined number, the distribution unit 136 distributes to users who have a history of accessing the first store based on the original setting of the retargeting advertisement.

  Further, the distribution unit 136 distributes the advertisement to a user who has a history of accessing the first store when the predetermined period has not passed until the end of the distribution period specified by the advertiser. When a predetermined period has passed until the end of the period, the advertisement distribution target may be extended to the target user for distribution. In this way, the distribution unit 136 can flexibly expand the target of distributing the advertisement or limit the target of the original retargeting advertisement in consideration of the remaining number of impressions of the advertisement and the period until the end of the distribution. Advertisement distribution may be performed.

[4. Web server configuration]
Next, the configuration of the web server 30 according to the embodiment will be described with reference to FIG. FIG. 9 is a diagram illustrating a configuration example of the web server 30 according to the embodiment. As shown in FIG. 9, the web server 30 includes a communication unit 31, a web content storage unit 32, and a control unit 33.

  The communication part 31 is implement | achieved by NIC etc., for example. The communication unit 31 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the user terminal 10 and the extraction device 100.

  The web content storage unit 32 is realized by, for example, a semiconductor memory device such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. And the web content memory | storage part 32 memorize | stores the information regarding web content (In the embodiment, the web page etc. which comprise a shopping mall). For example, the web content storage unit 32 stores an HTML file forming a web page, a still image or a moving image displayed on the web page. The web page stored in the web content storage unit 32 may include an advertisement frame for displaying an advertisement and a recommendation frame for displaying a recommendation. The web content storage unit 32 may store information regarding each store. For example, the web content storage unit 32 may store information on stores that are open in shopping malls, information on products that are handled by the stores, and the like.

  The control unit 33 is realized, for example, by executing various programs stored in a storage device inside the web server 30 using the RAM as a work area by a CPU, an MPU, or the like. The control unit 33 is realized by an integrated circuit such as an ASIC or FPGA, for example.

  As illustrated in FIG. 9, the control unit 33 includes a reception unit 34 and a distribution unit 35, and realizes or executes information processing functions and operations described below. The internal configuration of the control unit 33 is not limited to the configuration illustrated in FIG. 9, and may be another configuration as long as the information processing described later is performed. Further, the connection relationship between the processing units included in the control unit 33 is not limited to the connection relationship illustrated in FIG. 9, and may be another connection relationship.

  The accepting unit 34 accepts a web page acquisition request from the user terminal 10. For example, the reception unit 34 receives an HTTP request as a web page acquisition request.

  The distribution unit 35 distributes the web page to the user terminal 10 when the reception unit 34 receives a web page acquisition request. Specifically, the distribution unit 35 acquires an acquisition request target web page from the web content storage unit 32 and distributes the acquired web page to the user terminal 10. In addition, the distribution unit 35 may transmit information (for example, an access log to a store in a shopping mall or an action log for shopping) to the extraction device 100 regarding actions performed on the web page by the user terminal 10.

[5. Processing procedure)
Next, a processing procedure performed by the extraction apparatus 100 according to the embodiment will be described with reference to FIGS. 10 and 11. First, the procedure of the process in which the extraction apparatus 100 specifies a related store will be described with reference to FIG. FIG. 10 is a flowchart (1) illustrating a processing procedure according to the embodiment.

  As illustrated in FIG. 10, the extraction device 100 determines whether or not an advertisement has been accepted from the first store (step S <b> 101). When the advertisement submission is not received (step S101; No), the extraction apparatus 100 waits until the advertisement submission is received.

  On the other hand, when receiving an advertisement submission from the first store (step S101; Yes), the extraction device 100 acquires an inflow query of the first store (step S102). Then, the extraction device 100 performs a search using the acquired inflow query (step S103).

  Subsequently, the extraction device 100 counts the second higher-order store in the search result (step S104). Further, the extraction device 100 identifies a related store from the counted second stores (step S105). Then, the extraction device 100 stores the first store and the related store in the storage unit 120 in association with each other (step S106).

  Next, with reference to FIG. 11, a procedure of processing for extracting a target user to which the extraction apparatus 100 will distribute advertisements will be described. FIG. 11 is a flowchart (2) illustrating a processing procedure according to the embodiment.

  As illustrated in FIG. 11, the extraction device 100 determines whether or not the user terminal 10 has received an advertisement distribution opportunity (step S201). When the fact that the advertisement distribution opportunity has not been received has been received (step S201; No), the extraction device 100 stands by until it is received.

  On the other hand, when it is received that an advertisement distribution opportunity has occurred (step S201; Yes), the extraction apparatus 100 refers to the access information of the user who has generated the advertisement distribution opportunity (step S202). Then, the extraction apparatus 100 determines whether or not there is an access history to the related store in the access information of the user (step S203).

  When there is an access history to the related store (step S203; Yes), the extraction apparatus 100 extracts the user as a candidate for a delivery destination of the advertisement submitted from the first store (step S204). Further, the extraction apparatus 100 determines whether or not other distribution conditions such as user attributes are satisfied (step S205).

  When the user satisfies other distribution conditions (step S205; Yes), the extraction apparatus 100 distributes the advertisement submitted from the first store to the user (step S206).

  In addition, when there is no access history to an associated store (step S203; No), or when the user does not satisfy other distribution conditions (step S205; No), the extraction device 100 displays an advertisement selected according to a predetermined condition. Distribute to the user (step S207). For example, the extraction apparatus 100 selects an advertisement other than the advertisement submitted from the first store among the held advertisements, the distribution condition matching the user, and distributes the selected advertisement to the user.

[6. (Modification)
The extraction device 100 described above may be implemented in various different forms other than the above embodiment. Therefore, in the following, another embodiment of the extraction device 100 will be described.

[6-1. Store type
In the above embodiment, an example has been described in which the extraction device 100 specifies the related store of the first store among stores belonging to one shopping mall. Here, the store is not limited to a store belonging to one shopping mall, and may be a broader concept.

  For example, the extraction device 100 may regard each shopping mall scattered throughout the network as a store and execute the processing according to the embodiment. Specifically, the extraction device 100 receives an advertisement submitted from the administrator of one shopping mall, and specifies another shopping mall related to the one shopping mall. Then, the extraction apparatus 100 may extract a user having a history of accessing another shopping mall as a target user and distribute the extracted user to the target user who has extracted the advertisement of one shopping mall that submitted the advertisement.

  As described above, the store according to the embodiment is conceptual only, a related store can be specified in a certain store, and a retargeting advertisement can be distributed based on access information to the related store. If so, the store may be in any form.

[6-2. (Specify related store)
The extraction device 100 may explicitly accept the designation of the related store from the advertiser. Specifically, the extraction device 100 accepts designation of association between the submitted advertisement and a predetermined related store from the advertiser at an arbitrary timing. Then, the extraction apparatus 100 may preferentially distribute the advertisement to users who access a predetermined related store for which the designation is accepted among the target users.

  For example, the extraction device 100 identifies the second store specified by the first store as the competitive store as the predetermined related store. Then, the extraction device 100 associates the predetermined related store designated by the first store with the advertisement submitted from the first store. Note that the extraction device 100 may present a list of related stores identified based on the search result of the inflow query to the first store. In this case, the first store may select and specify a store handled as a predetermined related store among the related stores listed in the list.

  Then, the extraction device 100 has a user who has a history of accessing a predetermined related store for which designation has been accepted among target users when an advertisement distribution opportunity associated with the predetermined related store occurs. In this case, the advertisement is distributed preferentially to such users.

  Thereby, the extraction apparatus 100 can distribute the targeted advertisement to the customer of the related store that the first store is strongly aware of as the competitive store. As a result, the extraction device 100 can further improve the appeal effect of the advertisement distributed by the first store.

[6-3. Content type]
In the above-described embodiment, the extraction apparatus 100 has exemplified an advertisement related to a store belonging to a shopping mall or a product handled in the store as content to be distributed to the user. However, the extraction apparatus 100 may distribute content other than a store or a product.

  For example, the extraction apparatus 100 may distribute articles such as news and columns as content. Specifically, the extraction device 100 may distribute an article provided by one news site to a user who has accessed another news site competing with the one news site.

[6-4. (Medium)
In the above-described embodiment, the web page provided by the web server 30 is taken as an example of content serving as a medium for displaying an advertisement. However, the medium for displaying the advertisement is not limited to the web page. For example, the content serving as a medium may be a predetermined information application or a game application. Specifically, the medium for displaying the advertisement may be a banner frame included in a predetermined application.

  Further, the advertisement may be displayed together with the result of the search executed by the user. As described above, the extraction apparatus 100 can improve the advertising effect by distributing the advertisement to various media.

[6-5. (Use of search results)
In the above-described embodiment, an example has been described in which the extraction device 100 counts the upper second stores among the second stores searched by the inflow query and identifies the related stores. However, the extraction apparatus 100 does not necessarily need to count the upper second store among the second stores.

  For example, the extraction device 100 may count the second stores that are close to the ranking when the first store is searched for by the inflow query among the second stores searched by the inflow query. For example, when the first store is searched for by the inflow query and the rank is “20th”, the extraction device 100 is ranked from “15th” to “25th” when searched by the inflow query. The second store may be counted.

  Thereby, the extraction apparatus 100 may be able to specify the second store that is more likely to compete with the first store as the related store. In other words, stores that are closer in rank when searched by an inflow query are more likely to have similar business scales, products handled, and the like. Note that the extraction device 100 may count the second stores that are close in rank to the first store based on the rank of the search result, or rank the first store and rank based on the sales rank of the product that has become the inflow query. You may count the 2nd store where is near.

[6-6. (Validation of related stores)
The extraction apparatus 100 may perform verification on the specified related store after specifying the related store by the specifying process described in the above embodiment.

  For example, it is estimated that the number of users accessing the first store increases as the process according to the embodiment is performed and an advertisement is distributed to a user who has no history of accessing the first store. At this time, the extraction apparatus 100 acquires the ratio of users who have converted in both the first store and the related store among the users having a history of accessing the first store. Then, when the ratio of users who have converted in both the first store and the related store exceeds a predetermined threshold, the extraction apparatus 100 determines that the process that specified the related store is not an error. On the other hand, if the percentage of users who have converted in both the first store and the related store does not exceed a predetermined threshold, the extraction apparatus 100 determines that the process that specified the related store is an error. Also good.

  That is, when no conversion occurs in both, the extraction device 100 may determine that the specification as the related store was an error because both stores do not compete with each other. As described above, the extraction apparatus 100 can further improve the accuracy of the related store specifying process by generating feedback of its own process at a predetermined timing.

  In addition, when the number of users accessing the first store increases as the advertisement is distributed to users who have no history of accessing the first store, the extraction apparatus 100 determines the advertisement based on a predetermined criterion. The distribution method may be changed. For example, when the number of users who have access histories to the first store increases and it is determined that sufficient retargeting advertisements can be distributed, the extraction apparatus 100 extracts objects based on access information to related stores. You may make it interrupt the advertisement delivery to a user.

[6-7. Identification of related stores based on products)
The extraction device 100 may identify the related store of the first store based on the relevance of the products handled by each store.

  For example, the extraction device 100 acquires behavior information (such as purchase history and browsing history) of a user group in a shopping mall to which the first store belongs. Specifically, the extraction device 100 acquires user behavior information regarding a predetermined product (hereinafter referred to as “first product”) handled by an arbitrary store. Then, when the first store handles a product related to the first product (hereinafter referred to as “second product”), the extraction apparatus 100 selects a store that handles the first product as a related store of the first store. Is identified. In other words, the extraction device 100 identifies stores that handle related products as stores that are related to each other.

  Here, the extraction apparatus 100 determines the relevance between the first product and the second product based on various determination criteria. As an example, the extraction apparatus 100 specifies the second product from the arbitrary products based on the number of times or the ratio of the arbitrary product purchased together with the first product. Specifically, the extraction device 100 identifies a product that is frequently purchased from the user together with the first product as the second product in the shopping mall. Note that the extraction device 100 may specify the second product based on various statistical methods. For example, the extraction device 100 may specify a product purchased by a user exceeding a predetermined ratio among users who have purchased the first product at the same time as the second product. Alternatively, the extraction device 100 sets a predetermined threshold value in advance, and when the number of times that the user who purchased the first product simultaneously purchases the arbitrary product exceeds the predetermined threshold value, the extracting device 100 It may be specified as a product.

  In this case, the extraction apparatus 100 extracts the target user based on access information for the first product handled by the related store. Specifically, the extraction apparatus 100 extracts a user who has accessed the product page of the first product in the related store or a user who has purchased the first product in the related store as a target user.

  At this time, the extraction apparatus 100 may extract the target user as a candidate for a content providing destination related to the second product based on access information for the first product handled by the related store. That is, the extraction apparatus 100 may distribute an advertisement related to the second product to the target user as an advertisement related to the first store.

  It is estimated that a user who accesses the first product in the related store is highly likely to purchase the second product in the related store. Therefore, the extraction device 100 delivers an advertisement clearly indicating that the first store handles the second product to the user who has accessed the first product in the related store. That is, the extraction device 100 preferentially distributes the advertisement of the second product to a user who is interested in the first product that tends to be purchased together with the second product. Thereby, the extraction apparatus 100 can perform advertisement delivery with a higher appealing effect compared to the case of delivering advertisements to unspecified users. Moreover, the extraction apparatus 100 can attract the user to the first store by distributing the advertisement of the first store to the user who wants to purchase the second product in the related store.

  The extraction apparatus 100 may use a different method for determining the relevance between the first product and the second product. For example, the extraction device 100 specifies a second product from among arbitrary products based on the number or percentage of purchases of any product by any user who has a history of browsing the first product in any store. May be. That is, the extraction device 100 may specify a frequently purchased product as the second product in a user group having a history of browsing the first product even if the first product has not been purchased.

  In addition, the extraction device 100 may identify the second product based on whether the specifying unit 133 has product information that is the same as or similar to the first product or has a model number related to the first product. Good. Here, the product information is information indicating the characteristics of the product, such as category and attribute information set for the product. Generally, in shopping malls, categories (attributes) are set for the products handled by each store, and model numbers and other product information (for example, purchase layer, price range, other product identification information, etc.) assigned by manufacturers are displayed. The product is managed by setting. Therefore, the extraction device 100 can specify information about products from the shopping mall management side and refer to the acquired information to specify stores that handle similar products as related stores.

[7. Hardware configuration)
The extraction device 100, the user terminal 10, and the web server 30 according to the above-described embodiments are realized by a computer 1000 configured as shown in FIG. 12, for example. Hereinafter, the extraction apparatus 100 will be described as an example. FIG. 12 is a hardware configuration diagram illustrating an example of a computer 1000 that implements the functions of the extraction device 100. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, a HDD (Hard Disk Drive) 1400, a communication interface (IF) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700. Have

  The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 and controls each unit. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

  The HDD 1400 stores a program executed by the CPU 1100, data used by the program, and the like. The communication interface 1500 receives data from other devices via the communication network 500 (corresponding to the network N shown in FIG. 3), sends the data to the CPU 1100, and transmits the data generated by the CPU 1100 to the other devices via the communication network 500. Send to device.

  The CPU 1100 controls an output device such as a display and a printer and an input device such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Further, the CPU 1100 outputs the data generated via the input / output interface 1600 to the output device.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  For example, when the computer 1000 functions as the extraction device 100 according to the embodiment, the CPU 1100 of the computer 1000 implements the function of the control unit 130 by executing a program loaded on the RAM 1200. The HDD 1400 stores data in the storage unit 120. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired from other devices via the communication network 500.

[8. Others]
In addition, among the processes described in the above embodiment, all or part of the processes described as being automatically performed can be performed manually, or the processes described as being performed manually can be performed. All or a part can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the document and drawings can be arbitrarily changed unless otherwise specified. For example, the various types of information illustrated in each drawing is not limited to the illustrated information.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured. For example, the reception unit 131 and the acquisition unit 132 illustrated in FIG. 4 may be integrated. Further, for example, information stored in the storage unit 120 may be stored in a predetermined storage device provided outside via the network N.

  Moreover, in the said embodiment, the example which the extraction apparatus 100 performs the specific process which specifies a related store, and the extraction process which extracts an object user was shown. However, the above-described extraction device 100 may be separated into a specific device that performs a specific process and an extraction device that performs an extraction process. In this case, the specifying device has at least the specifying unit 133. The extraction device has at least an extraction unit 135. And the process by said extraction apparatus 100 is implement | achieved by the extraction system 1 which has each apparatus of a specific apparatus and an extraction apparatus.

  In addition, the above-described embodiments and modifications can be combined as appropriate within a range that does not contradict processing contents.

[9. effect〕
As described above, the extraction device 100 according to the embodiment includes the specifying unit 133 and the extraction unit 135. The specifying unit 133 specifies a related store that is a store related to the first store managed by a predetermined content provider. Based on the access information to the related store specified by the specifying unit 133, the extracting unit 135 extracts a target user who is a candidate for a predetermined content providing destination.

  As described above, the extraction apparatus 100 according to the embodiment extracts a target user who is a candidate of a predetermined content providing destination based on access information to a related store, and thus is not necessarily a user who has accessed the first store. In addition, the provider of the first store can be extracted as a provision destination of contents desired to be provided. Thereby, the extraction apparatus 100 can efficiently expand the distribution target users while maintaining the content appealing effect high.

  In addition, the extraction device 100 according to the embodiment further includes an acquisition unit 132 that acquires a query that outputs, as a search result, a first store or a product handled by the first store when input to a predetermined search engine. The specifying unit 133 specifies a related store based on a search result obtained when a query is input to a predetermined search engine.

  As described above, the extraction device 100 according to the embodiment specifies the related store based on the relevance obtained from the search result. Thereby, the extraction apparatus 100 can specify a store that can compete with the first store with high accuracy.

  In addition, the acquisition unit 132 acquires a query that triggers the user to access the first store. The specifying unit 133 specifies a related store based on a search result obtained when a query that triggers a user to access the first store is input to a predetermined search engine.

  As described above, the extraction device 100 according to the embodiment identifies the related store using the search result using the inflow query to the first store. Thereby, the extraction apparatus 100 can specify a store that can compete with the first store with high accuracy.

  The specifying unit 133 is a store or product that is output as a search result together with the first store or the first store when a query is input to a predetermined search engine, and is a store other than the first store. Based on the second store or the product handled by the second store, the related store is specified from the second store.

  As described above, the extraction device 100 according to the embodiment specifies the related store from the second store that is output as the search result together with the first store when the query is input to the search engine. Since it can be said that the stores searched by the same query are highly related, the extraction apparatus 100 can accurately specify a store highly related to the first store.

  Further, the specifying unit 133 specifies, as a related store, a second store that handles products whose sales order is equal to or higher than a predetermined order among the products searched by the query.

  As described above, the extraction device 100 according to the embodiment may specify the related store based on the sales of the product. Thereby, the extraction apparatus 100 can preferentially specify a store having competitiveness that can become a competition of the first store as the related store.

  The acquisition unit 132 acquires history information indicating that the user has converted in the related store. The extraction unit 135 extracts a target user based on the number or ratio of conversions in the related store.

  As described above, the extraction device 100 according to the embodiment can extract, for example, a user with a high willingness to purchase as a target user by acquiring a history such as conversion in the related store. For this reason, when the content is distributed, the extraction device 100 can extract a user who is assumed to have a higher content appeal effect.

  Further, the specifying unit 133 specifies a store other than the first store as a related store based on history information that a user having a history of conversion in the first store has converted in a store other than the first store. To do.

  Thus, the extraction device 100 according to the embodiment may specify a related store based on conversion between stores. That is, since the extraction apparatus 100 specifies not only a query search result but also a related store by various methods, the related store can be specified from a multifaceted viewpoint.

  Further, when the first store handles a second product that is a product related to the first product that is the predetermined product, the specifying unit 133 specifies the store that handles the first product as the related store. The extraction unit 135 extracts a target user based on access information for the first product handled by the related store.

  Thus, the extraction device 100 according to the embodiment may specify the related store based on the product handled by the store. Thereby, the extraction apparatus 100 can specify a related store from a multifaceted viewpoint.

  Further, the specifying unit 133 specifies the second product from among the arbitrary products based on the number of times or the ratio of the arbitrary product purchased together with the first product.

  As described above, the extraction device 100 according to the embodiment identifies a product that has a high tendency to be purchased together with the first product as the second product. Thereby, the extraction apparatus 100 can pinpoint the store where the user who becomes a purchase layer is similar as a related store accurately.

  In addition, the specifying unit 133 specifies the second product from among the arbitrary products based on the number or percentage of purchases of the arbitrary products by any user who has a history of browsing the first product in any store. To do.

  As described above, the extraction apparatus 100 according to the embodiment identifies a product that has a high tendency to be purchased from a user who has viewed the first product as the second product. Thereby, the extraction device 100 can identify stores that are easily accessible by users who have similar interests as related stores.

  Further, the specifying unit 133 specifies the second product based on whether the product information has the same or similar product information as the first product or has a model number related to the first product.

  As described above, the extraction device 100 according to the embodiment may specify the second product based on information set in the product. Thereby, the extraction device 100 can specify the second product based on the similarity of the product itself, not only based on the user's action.

  Further, the extraction unit 135 extracts the target user as a candidate for a content providing destination related to the second product based on the access information for the first product handled by the related store.

  As described above, the extraction device 100 according to the embodiment may extract a user as a distribution target of content related to the second product handled in the first store (for example, an advertisement promoting the second product). Thereby, the extraction apparatus 100 can preferentially extract a user who is assumed that the distributed content exhibits a high appealing effect.

  In addition, the extraction apparatus 100 according to the embodiment distributes the reception unit 131 that accepts submission of predetermined content and the predetermined content received by the reception unit 131 to the target user extracted by the extraction unit 135. And a delivery unit 136.

  As described above, the extraction apparatus 100 according to the embodiment can improve the appeal effect of the content to be distributed by distributing the content by narrowing the distribution destination to the target user.

  The accepting unit 131 accepts designation of association between the predetermined content and the predetermined related store from the provider of the predetermined content. The distribution unit 136 preferentially distributes predetermined content to users who access a predetermined related store whose designation is received by the reception unit 131 among the target users.

  As described above, the extraction device 100 according to the embodiment may perform content distribution based on access information to a specified related store. Thereby, the extraction apparatus 100 can perform content distribution focused on the customers of the store that the first store is aware of as a competition.

  The accepting unit 131 accepts designation of the number of deliveries for delivering predetermined content to the user. The distribution unit 136 distributes the predetermined content to the target user when the remaining number of the specified distribution number exceeds the predetermined number, and the remaining number of the specified distribution number is equal to or less than the predetermined number. In this case, the predetermined content is distributed to a user who has a history of accessing the first store.

  As described above, the extraction device 100 according to the embodiment may expand the users as distribution destinations based on the remaining number of contents. As a result, the extraction apparatus 100 can perform a distribution process that balances the distribution of content to more targets and the effective distribution focused on retargeting distribution.

  The accepting unit 131 accepts designation of a delivery period for delivering predetermined content to the user. When the predetermined period has not passed until the end of the specified distribution period, the distribution unit 136 distributes the predetermined content to a user who has a history of accessing the first store, When a predetermined period has passed until the end, the distribution target of the predetermined content is extended to the target user and distributed.

  As described above, the extraction device 100 according to the embodiment may expand the users who are the distribution destinations based on the distribution period. Thereby, the extraction apparatus 100 can perform a distribution process in which content is reliably distributed during a designated period and effective distribution focused on retargeting distribution is achieved at the same time.

  The embodiment of the present application has been described in detail with reference to the drawings. However, this is an exemplification, and various modifications and improvements are made based on the knowledge of those skilled in the art including the aspects described in the column of the disclosure of the invention. The present invention can be implemented in other forms.

  In addition, the “section (module, unit)” described above can be read as “means” or “circuit”. For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

DESCRIPTION OF SYMBOLS 1 Extraction system 10 User terminal 30 Web server 100 Extraction apparatus 110 Communication part 120 Storage part 121 Advertisement information storage part 122 Store related information storage part 123 Search result table 124 Related table 125 Access information storage part 130 Control part 131 Reception part 132 Acquisition part 133 Identification unit 134 Reception unit 135 Extraction unit 136 Distribution unit

Claims (20)

A specifying unit for specifying a related store that is a store related to a first store managed by a provider of predetermined content;
An extraction unit that extracts a target user who is a candidate for a destination of the predetermined content based on access information to the related store identified by the identification unit;
An acquisition unit for acquiring a query related to the first store or a product handled by the first store;
Equipped with a,
The acquisition unit
When input to a predetermined search engine, obtain a query that causes the first store or the product handled by the first store to be output as a search result,
The specific part is:
When the query is input to a predetermined search engine, the first store or a store or product output as a search result together with the first store, the second store being a store other than the first store or Based on the products handled by the second store, the related store is identified from the second stores.
An extraction device characterized by that. The acquisition unit
Get a query that triggered the user access to the first store,
The specific part is:
Identifying the related store based on a search result obtained when a query that triggers a user to access the first store is input to a predetermined search engine;
The extraction device according to claim 1 . The specific part is:
A second store that handles products whose sales order is a predetermined rank or higher among the products searched by the query is specified as the related store.
The extraction device according to claim 1 . The acquisition unit
Obtain historical information indicating that the user has converted in the related store,
The extraction unit includes:
Extracting the target user based on the number or percentage of conversions in the related store;
The extraction device according to any one of claims 1 to 3 , wherein The specific part is:
A user having a history of conversion in the first store identifies a store other than the first store as a related store based on history information converted in a store other than the first store.
The extraction device according to any one of claims 1 to 4 , wherein A specifying unit for specifying a related store that is a store related to a first store managed by a provider of predetermined content;
An extraction unit that extracts a target user who is a candidate for a destination of the predetermined content based on access information to the related store identified by the identification unit;
With
The specific part is:
When the first store handles the second product that is related to the first product that is the predetermined product, the store that handles the first product is identified as the related store,
The extraction unit includes:
Based on the access information for the first product handled by the related store, the target user is extracted as a candidate for providing the content related to the second product,
An extraction device characterized by that. The specific part is:
Based on the number or percentage of purchase of any product together with the first product, the second product is identified from the arbitrary product.
The extraction apparatus according to claim 6 . The specific part is:
An arbitrary user having a history of browsing the first product in an arbitrary store specifies the second product from the arbitrary product based on the number of times or the ratio of purchasing the arbitrary product,
The extraction apparatus according to claim 6 . The specific part is:
Identifying the second product based on whether it has product information that is the same or similar to the first product or has a model number associated with the first product;
The extraction apparatus according to any one of claims 6 to 8 , wherein A specifying unit for specifying a related store that is a store related to a first store managed by a provider of predetermined content;
An extraction unit that extracts a target user who is a candidate for a destination of the predetermined content based on access information to the related store identified by the identification unit;
An accepting unit for accepting submission of the predetermined content;
A distribution unit that distributes the predetermined content received by the reception unit to a target user extracted by the extraction unit;
With
The reception unit
Accepting designation of the number of distributions for distributing the predetermined content to the user,
The delivery unit
When the remaining number of the specified number of distributions exceeds a predetermined number, the predetermined content is distributed to the target user, and when the remaining number of the specified number of distributions is equal to or less than the predetermined number , Delivering the predetermined content to users having a history of accessing the first store,
An extraction device characterized by that. A specifying unit for specifying a related store that is a store related to a first store managed by a provider of predetermined content;
An extraction unit that extracts a target user who is a candidate for a destination of the predetermined content based on access information to the related store identified by the identification unit;
An accepting unit for accepting submission of the predetermined content;
A distribution unit that distributes the predetermined content received by the reception unit to a target user extracted by the extraction unit;
With
The reception unit
Accepting designation of a delivery period for delivering the predetermined content to the user,
The delivery unit
If the predetermined period has not passed until the end of the specified distribution period, the predetermined content is distributed to a user having a history of accessing the first store, and the predetermined period until the end of the specified distribution period If it has passed, the distribution target of the predetermined content is expanded and distributed to the target user.
An extraction device characterized by that. The reception unit
Accepting designation of association between the predetermined content and a predetermined related store from a provider of the predetermined content;
The delivery unit
Distributing the predetermined content preferentially to users who have accessed a predetermined related store whose designation has been received by the receiving unit among the target users.
The extraction device according to claim 10 or 11 , wherein An extraction method performed by a computer,
A specifying step of specifying a related store that is a store related to a first store managed by a provider of predetermined content;
An extraction step of extracting a target user who is a candidate for a destination of the predetermined content based on access information to the related store specified by the specifying step;
An acquisition step of acquiring a query related to the first store or a product handled by the first store;
Including
The acquisition step includes
When input to a predetermined search engine, obtain a query that causes the first store or the product handled by the first store to be output as a search result,
The specific process includes
When the query is input to a predetermined search engine, the first store or a store or product output as a search result together with the first store, the second store being a store other than the first store or Based on the products handled by the second store, the related store is identified from the second stores.
An extraction method characterized by that. A specific procedure for identifying a related store that is a store related to a first store managed by a provider of predetermined content;
An extraction procedure for extracting a target user who is a candidate for a destination of the predetermined content based on access information to the related store identified by the identification procedure;
An acquisition procedure for acquiring a query related to the first store or a product handled by the first store;
To the computer,
The acquisition procedure is as follows:
When input to a predetermined search engine, obtain a query that causes the first store or the product handled by the first store to be output as a search result,
The specific procedure is:
When the query is input to a predetermined search engine, the first store or a store or product output as a search result together with the first store, the second store being a store other than the first store or Based on the products handled by the second store, the related store is identified from the second stores.
An extraction program characterized by that. An extraction method performed by a computer,
A specifying step of specifying a related store that is a store related to a first store managed by a provider of predetermined content;
An extraction step of extracting a target user who is a candidate for a destination of the predetermined content based on access information to the related store specified by the specifying step;
With
The specific process includes
When the first store handles the second product that is related to the first product that is the predetermined product, the store that handles the first product is identified as the related store,
The extraction step includes
Based on the access information for the first product handled by the related store, the target user is extracted as a candidate for providing the content related to the second product,
An extraction method characterized by that. A specific procedure for identifying a related store that is a store related to a first store managed by a provider of predetermined content;
An extraction procedure for extracting a target user who is a candidate for a destination of the predetermined content based on access information to the related store identified by the identification procedure;
To the computer,
The specific procedure is:
When the first store handles the second product that is related to the first product that is the predetermined product, the store that handles the first product is identified as the related store,
The extraction procedure is:
Based on the access information for the first product handled by the related store, the target user is extracted as a candidate for providing the content related to the second product,
An extraction program characterized by that. An extraction method performed by a computer,
A specifying step of specifying a related store that is a store related to a first store managed by a provider of predetermined content;
An extraction step of extracting a target user who is a candidate for a destination of the predetermined content based on access information to the related store specified by the specifying step;
An accepting step for accepting submission of the predetermined content;
A distribution step of distributing the predetermined content received by the reception step to a target user extracted by the extraction step;
With
The reception process includes
Accepting designation of the number of distributions for distributing the predetermined content to the user,
The delivery step includes
When the remaining number of the specified number of distributions exceeds a predetermined number, the predetermined content is distributed to the target user, and when the remaining number of the specified number of distributions is equal to or less than the predetermined number , Delivering the predetermined content to users having a history of accessing the first store,
An extraction method characterized by that. A specific procedure for identifying a related store that is a store related to a first store managed by a provider of predetermined content;
An extraction procedure for extracting a target user who is a candidate for a destination of the predetermined content based on access information to the related store identified by the identification procedure;
A reception procedure for accepting submission of the predetermined content;
A delivery procedure for delivering the predetermined content accepted by the acceptance procedure to a target user extracted by the extraction procedure;
To the computer,
The reception procedure is as follows:
Accepting designation of the number of distributions for distributing the predetermined content to the user,
The delivery procedure is:
When the remaining number of the specified number of distributions exceeds a predetermined number, the predetermined content is distributed to the target user, and when the remaining number of the specified number of distributions is equal to or less than the predetermined number , Delivering the predetermined content to users having a history of accessing the first store,
An extraction program characterized by that. An extraction method performed by a computer,
A specifying step of specifying a related store that is a store related to a first store managed by a provider of predetermined content;
An extraction step of extracting a target user who is a candidate for a destination of the predetermined content based on access information to the related store specified by the specifying step;
An accepting step for accepting submission of the predetermined content;
A distribution step of distributing the predetermined content received by the reception step to a target user extracted by the extraction step;
With
The reception process includes
Accepting designation of a delivery period for delivering the predetermined content to the user,
The delivery step includes
If the predetermined period has not passed until the end of the specified distribution period, the predetermined content is distributed to a user having a history of accessing the first store, and the predetermined period until the end of the specified distribution period If it has passed, the distribution target of the predetermined content is expanded and distributed to the target user.
An extraction method characterized by that. A specific procedure for identifying a related store that is a store related to a first store managed by a provider of predetermined content;
An extraction procedure for extracting a target user who is a candidate for a destination of the predetermined content based on access information to the related store identified by the identification procedure;
A reception procedure for accepting submission of the predetermined content;
A delivery procedure for delivering the predetermined content accepted by the acceptance procedure to a target user extracted by the extraction procedure;
To the computer,
The reception procedure is as follows:
Accepting designation of a delivery period for delivering the predetermined content to the user,
The delivery procedure is:
If the predetermined period has not passed until the end of the specified distribution period, the predetermined content is distributed to a user having a history of accessing the first store, and the predetermined period until the end of the specified distribution period If it has passed, the distribution target of the predetermined content is expanded and distributed to the target user.
An extraction program characterized by that.

Images