JP6698730B2 - Extraction device, extraction method, and extraction program - Google Patents

Description

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

  2. Description of the Related Art Conventionally, there is a method called retargeting advertisement as a method of delivering advertisements via the Internet. Such a method is, for example, displaying advertisement content having a link to the predetermined website on a user terminal of a user who has accessed the predetermined website, and urges the user to access the predetermined website.

  As a technique related to the above-described advertisement delivery, there is known a technique of delivering an advertisement to a user who has visited a website similar to the website provided by the advertiser. In addition, there is known a technique of delivering an advertisement based on information associated with a notification tag included in a web page.

JP, 2016-62370, A JP, 2016-177650, A

  However, there is room for further improvement in effective advertisement distribution to users. For example, in the conventional technology, although an advertisement can be delivered to a user who visits a website similar to a website provided by an advertiser or a user who visits a page provided with a notification tag, the advertisement can be delivered to other users. Therefore, there is a possibility that effective advertisement distribution may not be possible. It should be noted that the problems related to such distribution are common not only in the distribution of advertisements but also in the distribution of information contents such as moving image contents and product recommendations.

  The present application has been made in view of the above, and an object of the present invention is to provide an extraction device, an extraction method, and an extraction program capable of efficiently expanding a distribution target user while maintaining a high content appealing effect. To do.

  The extraction device according to the present application is a store that is related to a first store managed by a provider of predetermined content and that is a store that opens in the same shopping mall as the shopping mall in which the first store opens. A specifying unit that specifies the specifying unit; and an extracting 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 specified by the specifying unit. To do.

  According to an aspect of the embodiment, it is possible to efficiently expand the distribution target users while maintaining a high content appealing effect.

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 showing an example of a search result table according to the embodiment. FIG. 7 is a diagram illustrating an example of the association 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) showing a processing procedure according to the embodiment. FIG. 11 is a flowchart (2) showing the processing procedure according to the embodiment. FIG. 12 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the extraction device.

  Hereinafter, modes (hereinafter, referred to as “embodiments”) for carrying out the extraction device, the extraction method, and the extraction program according to the present application will be described in detail with reference to the drawings. Note that the extraction device, the extraction method, and the extraction program according to the present application are not limited by this embodiment. Further, the respective embodiments can be appropriately combined within the range in which the processing content is not inconsistent. Also, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicate description will be omitted.

[1. Example of extraction processing]
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 device 100 according to the present application specifies a related store that is a store related to a store managed by a provider of the predetermined content, and based on access information to the related store, the predetermined content is extracted. An example in which a process of extracting a user who is a candidate for a provision destination is performed will be described.

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

  In the embodiment, it is assumed that the provider of the predetermined content desires to deliver the advertisement, which he has submitted, to the user as a retargeting advertisement. Retargeting advertisements are advertisements delivered to users who have accessed the first store in the past, and since advertisements that match the interests and interests of users can be delivered, they are generally considered to have a high advertising effect. However, since the retargeting advertisement is distributed based on the history of the user's access to the first store in the past, it cannot be distributed to the user who has no history of accessing the first store. Therefore, it is difficult to deliver the number of retargeting advertisements requested by the provider when the number of accesses to the first store is insufficient or when the first store has just opened in a shopping mall. There are cases.

  Therefore, the extraction device 100 according to the embodiment identifies a related store that is a store related to the first store, and, based on access information to the related store, a user (hereinafter, referred to as a candidate for a destination to which predetermined content is provided) , "Target user").

  For example, the extraction device 100 identifies a related store related to the first store from the second stores. In other words, the store related to the first store in the same shopping mall is a store that competes with the first store, and it is presumed that the collection of products and the like required by a user who is a customer is similar to each other. Although the extraction device 100 has no history of accessing the first store, it can perform processing such as distributing advertisements of the first store to target users by extracting target users who have accessed related stores. . That is, according to the extraction device 100, the provider of the predetermined content can cause the user who accesses the store competing with the first store to deliver his/her advertisement. Therefore, the provider of the predetermined content can efficiently deliver the 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 a commercial transaction, and is a concept including not only a product but also services and the like. Hereinafter, with reference to FIG. 1, an example of the extraction process performed by the extraction device 100 will be described along the flow.

  The extraction device 100 illustrated in FIG. 1 is a server device that receives the submission of an advertisement from the administrator of the first store and delivers the received advertisement to the user. Further, as described below, the extraction device 100 identifies a related store of the first store and extracts a user who is a candidate for an advertisement delivery destination based on access information to the related store.

  The shopping mall AAA is an example of a shopping mall operated on a network. The store B01 and the store B02 are examples of stores opened in the shopping mall AAA. In the example of FIG. 1, the store B01 is the first store and the store B02 is the second store. Further, in the following description, the action performed by the store administrator or the like may be replaced with the action performed by the store. For example, the fact that the administrator of the store B01 submits an advertisement may be described as “the store B01 submits an advertisement”.

The user terminals 10 ₁ and 10 ₂ shown in FIG. 1 are information processing terminals used by users. 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. The user U01 or the user U02 accesses the web server 30 (see FIG. 3) via the user terminals 10 ₁ and 10 ₂ to access the website (shopping mall AAA in the example of FIG. 1) provided by the web server 30. To use. In the following, the user terminal 10 ₁ and the user terminal 10 ₂ will be collectively referred to as the “user terminal 10” unless it is necessary to distinguish them. Further, when it is not necessary to distinguish between the user U01 and the user U02, they are simply referred to as “user”. In the following, the user terminal 10 and the user who uses the user terminal 10 may be identified with each other. For example, "sends the content to the user U01", in fact, may mean that the "transmitting the content to the user terminal 10 ₁ user U01 to use". Although not shown in FIG. 1, the user U01 and the user U02 do not indicate a single user but may indicate the existence of a plurality of users.

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

After that, the user U01 who uses the shopping mall AAA executes a process of 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 performing the search action (step S13). At this time, the extraction device 100 acquires information regarding 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, the access information indicating that the user U01 has accessed the store B01 after the search, and the like. Then, the extraction device 100 identifies the related store of the store B01 based on the search result (step S15). The details of this identifying process will be described later.

  In the example of FIG. 1, the extraction device 100 specifies the store B02 as a related store of the store B01. The extraction device 100 appropriately stores the relationship between the identified 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 device 100 stores the store B01 and the store B02 in the store related information storage unit 122 in association with each other.

  After that, 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 the 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 device 100 extracts the user U02 as a target user related to the store B01 based on the history of the user B02 accessing the store B02 which is a related store of the store B01. Then, the extraction device 100 delivers 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 a related store related to the first store, and identifies the candidate of the distribution destination of the advertisement of the first store based on the access information to the store B02. Extract target users.

  That is, the extraction device 100 according to the embodiment delivers the retargeting advertisement of the store B01 by using the access information to the store B02 which is the related store, even when the access to the store B01 is not sufficient. It is possible to extract a target user as a delivery destination. In other words, the extraction device 100 can extend the delivery destination of the retargeting advertisement of the store B01 to a user such as the user U02 who does not actually have a history of access to the store B01. Further, since the store B02 is likely to be a store that competes with the store B01, it is assumed that the interests of the users as customers are close to each other. Therefore, it is estimated that the advertisement of the store B01 exerts a high appealing effect on the user who is the customer of the store B02. In this way, the extraction device 100 can expand users to be distribution destinations while maintaining high advertising appeal effect.

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

  That is, there is a case where a content (web page) in the shopping mall AAA has a function implemented by a web beacon or the like for notifying information about a user (hereinafter referred to as “user information”). 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 (also referred to as “clear GIF”) stored in the extraction device 100. Thereby, the extraction device 100 can receive and acquire the user information from the user terminal 10. For example, the extraction device 100 uses the function realized by the web beacon so that the user U01 accesses the first store, browses the product, purchases the product, and sends an advertisement on the user terminal 10. You can receive information such as clicked information.

  By the way, as described above, in order to expand users who are distribution destinations while maintaining a high advertising appeal effect, it is desirable that the extraction device 100 accurately specify a related store. With respect to this point, the details of the specifying process performed by the extraction device 100 will be described with reference to FIG. 2.

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 selects the store B01 from the displayed stores. Specifically, the user U01 touches the link 68 with 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 flown into the store B01 triggered by the search using the query “product A01”.

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

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

  For example, the extraction device 100 extracts the second store searched for each query, as in the table 70 shown in FIG. For example, in the table 70 shown in FIG. 2, the query “commodity A01” indicates that “B02”, “B03”, and “B04” have been retrieved as the second store. Further, if the query is “commodity A02”, it indicates that “B02”, “B05”, or “B07” has been retrieved as the second store.

  Since the query “commodity A01” and the query “commodity 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. Can be said to be a store that deals with, that is, a competitive store. Then, the extraction device 100 extracts the second store searched by using the plurality of queries and counts the number of the extracted second stores.

  Then, the extraction device 100 identifies 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 the second stores in order of increasing counted number as a related store. As a result, the extraction device 100 can accurately extract a store that is expected to compete with the first store and identify it as a related store. In the example of FIG. 2, the extraction device 100 identifies the store “B02”, the store “B03”, or the store “B05” among the second stores as the related store of the first store, as shown in Table 72. To do.

  Note that the identification processing shown in FIG. 2 is an example, and the extraction device 100 may identify the related store by various methods. For example, the extraction device 100 may previously accept input of definition data between related stores from the administrator of the extraction device 100 or the manager of the shopping mall AAA, and may specify the related store based on the definition data. .. Alternatively, the extraction device 100 acquires the product list of the stores belonging to the shopping mall AAA and opens the second store in response to the purchase of the product handled by the first store from the user in the second store. It may be specified as a related store.

  Note that the queries extracted by the extraction device 100 described above are examples, and the extraction device 100 may be any query as long as it is a query that triggers the flow of the user U01 into the first store as well as the product name. May be obtained.

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

[2. Configuration of extraction system]
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 showing 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 devices are communicatively connected by wire or wirelessly via a network N (for example, the Internet). 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, a smart phone, a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), an information processing device such as a wearable device (Wearable Device). Is. The user terminal 10 acquires the web page from the website provided by 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 is a search service site, auction site, news site, weather forecast site, finance (stock price) site, route search site, map providing site, travel site, restaurant introduction site, web site. Various web pages related to blogs may be provided.

  The web page delivered by the web server 30 may include a recommendation frame or an advertisement frame for displaying a recommendation or an advertisement. Then, the web page including the recommendation frame and the advertisement frame includes an acquisition command for acquiring the recommendation and the 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 the recommendation or advertisement from the extraction apparatus 100 by accessing the URL described in the HTML file or the like.

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

  The extraction device 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 identified related store, a candidate for the provision destination of the predetermined content. It is a server device for extracting target users to be

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

[3. Configuration of extraction device]
Next, the configuration of the extraction device 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 information. You may have.

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

(About 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 (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.

(About advertisement information storage unit 121)
The advertisement information storage unit 121 stores information about 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 stores the “advertiser store ID (first store ID)”, “advertisement ID”, “distribution condition”, “impression number”, “impression guarantee number”, and “impression guarantee number”. It has an item such as “delivery period”.

  The “advertiser store ID (first store ID)” indicates identification information that identifies the store that is the advertiser. The “advertisement ID” indicates identification information that identifies an advertisement. In this specification, the identification information as shown in FIG. 5 is the same as the reference numeral 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. In FIG. 5, an example in which conceptual information such as “E01” is stored in the distribution condition is shown. In reality, the item of the distribution condition indicates whether or not the advertisement is a retargeting advertisement, or Information such as designation of user attribute information (age, sex, etc.) extracted as a delivery destination, designation of content of a medium (web page) having an advertisement frame as a delivery destination, and the like are stored.

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

  The “delivery period” indicates a period during which the advertisement is delivered. For example, the extraction device 100 performs the delivery for the guaranteed number of impressions before the delivery period elapses for the advertisement for which the delivery period is set.

  That is, in the example shown in FIG. 5, it is indicated that the store B01 whose advertiser store ID (first store ID) is “B01” is uploading the advertisement C01 identified by the advertisement ID “C01”. There is. Further, the distribution condition of the advertisement C01 is “E01”, the current number of impressions is “5000”, the guaranteed number of impressions designated by the store B01 which is the advertiser is “20,000”, and the distribution period is “ “April 1, 2017 to June 30, 2017”.

  Although not shown in FIG. 5, the advertisement information storage unit 121 may further store 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 relationships. The store related information storage unit 122 according to the embodiment has a search result table 123 and a related table 124 as data tables. Hereinafter, each data table will be described in order.

(About the search result table 123)
The search result table 123 stores a query that triggered a 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 showing an example of the search result table 123 according to the embodiment. In the example shown in FIG. 6, the search result table 123 has items such as “first store ID”, “search information”, and “sales information”. Also, the "search information" has small items such as "inflow query" and "second store ID". Further, the “sales information” has small items such as “sales rank” and “sales rank of first store”.

  The “first store ID” corresponds to the advertiser store ID shown in FIG. The “search information” indicates the result information of the search performed by the query that triggered the user to flow into the first store. The “inflow query” indicates the query that triggered the inflow of the user into the first store. The “second store ID” is identification information that identifies the second store. The second store ID shown in FIG. 5 represents the identification information of the second store displayed as the search result when the search is performed by the inflow query.

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

  That is, in the example illustrated in FIG. 6, the inflow query of the store B01, which is the first store, is, for example, “product A01” or “product A02”. Further, when the search is performed for “commodity A01”, the second store displayed in the search result is, for example, the second store ID “B02”, “B03”, “B04”, “B07”, or the like. Is shown. In addition, among the second stores searched, the store with the highest sales rank in the product A01 is the store B02, the store with the second sales rank is the store B03, and the store with the fourth sales rank is the store. Indicates that the store is store B04, and the store with the fifth highest sales ranking is store B07. In addition, the store B01, which is the first store, indicates that the sales rank of the product A01 is “3rd place”.

(About the related table 124)
The related table 124 stores information about related stores. FIG. 7 shows an example of the association table 124 according to the embodiment. FIG. 7 is a diagram showing an example of the association table 124 according to the embodiment. In the example shown in FIG. 7, the related table 124 has 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 about the second store. The “search result information” indicates information on the 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 reality, the items of the search result information include the keyword corresponding to the inflow query and the number of inflow queries. In addition, statistical information such as date and time information when the search is performed is stored. The search result information may be updated at any time, for example, 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 the second store has appeared as a result of a search performed by a plurality of inflow queries. If the same store appears twice or more in the search result by one inflow query, the extraction device 100 may uniquely count the stores that appear multiple times, or it may count the number of appearances as it is. May be.

  The “related store” indicates the identification information of the store identified as the 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 the second stores in the descending order of appearance frequency.

  That is, in the example illustrated in FIG. 7, the search result information associated with the store B01 that is the first store is “F01”, and the second store that appears as a search result in the search result information is, for example, “B02”. , “B03”, “B04”, “B05”, “B06”, “B07”, “B08”, and the like. Also, for example, the number of times "B02" has appeared as a search result is "165", the number of times "B03" has been appeared is "135", and the like. Then, the second store identified as the related store related to the store B01 which is the first store is, for example, “B02”, “B03”, “B05”, “B08”, “B07”, It indicates that it is "B12", "B16", or the like.

(About access information storage unit 125)
The access information storage unit 125 stores various information regarding the user, including the access information of the user. FIG. 8 shows 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 shown in FIG. 8, the access information storage unit 125 has items such as “user ID”, “attribute information”, “access information”, “conversion information”, and “reaction information”.

  The “user ID” indicates identification information for identifying the user or the user terminal 10. The “attribute information” indicates attribute information such as gender and age of the user. The “access information” indicates information regarding access such as the number of times the user has accessed the store and the date and time. The “conversion information” indicates information regarding conversion such as the number of times the user has reached a conversion (for example, purchasing a product, etc.) in the store, the date and time, and the like. The “reaction information” indicates information regarding the reaction to the advertisement, such as the number and rate of clicks on the advertisement by the user and the time and number of times the advertisement was viewed.

  In the example shown in FIG. 8, information stored in “attribute information”, “access information”, “conversion information”, and “reaction information” is set to “G01”, “H01”, “J01”, or “K01”. However, in practice, specific information is stored in each item. For example, the attribute information stores attribute information such as gender, age, place of residence, family structure, and annual income of the user. Further, in the reaction information, information is stored that statistics the number and frequency of clicks on distributed advertisements and the number and frequency of conversions to advertisements. The extraction device 100 may represent the reaction information with a predetermined score. For example, the extraction device 100 may calculate the score regarding the reaction information according to the click on the advertisement, the number of conversions, the rate, and the like. Then, the extraction device 100 may perform an adjustment process such as preferentially delivering a predetermined product to a user who easily reacts to an advertisement. Also, the reaction information may be generated for each store. For example, in the extraction process, the extraction device 100 may make an adjustment such that the store is likely to be advertised to a user who frequently reacts to an advertisement of 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”, and a response. It indicates that the information is “K01”.

(Regarding the control unit 130)
The control unit 130 is a controller, and is, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like, which stores various programs (an example of an extraction program) stored in a storage device inside the extraction apparatus 100. (Corresponding) is executed by using the RAM as a work area. The control unit 130 is a controller and is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

  As illustrated 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, and information described below. Realize or execute processing functions and actions. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 4, and may be another configuration as long as it is a configuration for performing information processing described later. 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 reception unit 131 receives the submission of predetermined content. Specifically, the reception unit 131 receives the submission of the advertisement from the store that desires to deliver the advertisement. Further, the acceptance unit 131 may accept distribution conditions such as distribution of the advertisement as a retargeting advertisement when the advertisement is submitted.

  Further, the acceptance unit 131 may accept designation of the number of distributions for distributing the advertisement to the user when the advertisement is submitted. That is, the reception unit 131 receives from the advertiser the designation of the guaranteed number of impressions.

  Further, the acceptance unit 131 may accept designation of a distribution period for distributing 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 the distribution condition.

  The reception unit 131 appropriately stores the received information about the advertisement in the storage unit 120. For example, the reception unit 131 stores the received information about the advertisement in the advertisement information storage unit 121.

(About acquisition unit 132)
The acquisition unit 132 acquires various kinds of information. For example, the acquisition unit 132 acquires a query related to the 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.

  The acquisition unit 132 may also acquire the query that triggered 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.

  In addition, the acquisition unit 132 may acquire information regarding a user who uses the shopping mall. For example, the acquisition unit 132 acquires information that the user has accessed an arbitrary store in the shopping mall. In addition, the acquisition unit 132 may acquire the action log of the user in the shopping mall. Specifically, the acquisition unit 132 may acquire history information indicating that the user has reached conversion in the store.

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

  In addition, the acquisition unit 132 may acquire the user's reaction to the advertisement when the advertisement is delivered to the user. For example, the acquisition unit 132 acquires at least one of the number or rate of advertisements selected (clicked or touched) by the user, or the number or rate of conversions related to the advertisement, as the response of the user to the advertisement. To do. The conversion related to the advertisement indicates, for example, that the store that is the link destination of the advertisement is accessed, that the user actually purchased the advertised product, or the like. Further, the acquisition unit 132 may acquire an index value indicating the appealing effect such as CTR (Click Through Rate) and CVR (Conversion Rate).

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

  In addition, the acquisition unit 132 may appropriately acquire the information stored in the storage unit 120. In addition, the acquisition unit 132 may store the acquired information in the storage unit 120 as appropriate. For example, the acquisition unit 132 stores the acquired information about the query in the store-related information storage unit 122.

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

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

  More specifically, the specifying unit 133 is a store or a product that is output as a search result together with the first store when the 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 which is the store of the second store or the product handled by the second store. For example, the specifying unit 133 performs a search process using a plurality of queries, and specifies the second store, which has a large number counted as a search result, as a related store.

  The identifying 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 the store or the product included in the text data (snippet or the like) output as the search result, specify the store name or the product name, and count the specified number. Further, the specifying unit 133 may specify the store to be the link destination based on the link information output as the search result and count the specified number.

  Further, the identifying unit 133 may identify, as a related store, a second store that handles products whose sales order is a predetermined rank or more among the products searched by the query. In other words, the identifying unit 133 may make adjustment so that the higher the store is output as the search result, the more the store is identified as the related store. Specifically, the identifying unit 133 may identify the related store by targeting the stores that are output to the top (for example, within the 20th place) as a search result. Accordingly, 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 by using only the search result. For example, the identifying unit 133 may identify the related store based on the action history of the user. Specifically, the identifying unit 133 uses the history information that the user who has the history of conversion in the first store has converted in a store (second store) other than the first store, based on the second store. May be identified as a related store.

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

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

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

(About the extraction unit 135)
The extraction unit 135 extracts a target user who is a candidate for the provision destination of the predetermined content, based on the access information to the related store identified by the identification unit 133. For example, when the receiving unit 134 receives the notification that the 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 has generated the advertisement distribution opportunity. Note that the extraction unit 135 may extract the target user in advance as the distribution destination of the advertisement in the first store before the reception unit 134 receives the notification 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 has accessed the related store, the ratio of the access in the shopping mall to the related store, or the like. Specifically, the extraction unit 135 preferentially extracts a user who has a higher number of times or a higher percentage of accessing the related store as a target user.

  Note that the extraction unit 135 may extract the target user based not only on the presence or 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 the target users as the number of times or the ratio of the conversion in the related store increases. It can be said that a user having a large number of conversions or a high percentage of conversions in the related store is a user who frequently purchases in a store competing with the first store. The extraction unit 135 can increase the chances that the advertisement of the first store is delivered to the user by preferentially extracting the user as the target user. As a result, the extraction unit 135 can attract users who are customers from the competing second store to the first store.

(About the distribution unit 136)
The delivery unit 136 delivers various types of information. For example, the distribution unit 136 distributes the advertisement received by the reception unit 131 to the target users extracted by the extraction unit 135. The delivery unit 136 may further match the target user extracted by the extraction unit 135 with the delivery condition set for each advertisement, and deliver the advertisement to the matched users. For example, the delivery unit 136 may deliver a advertisement by selecting, from among the target users, a user who meets conditions such as sex and age specified by the advertiser.

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

  Further, the delivery unit 136 delivers 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 delivery period designated by the advertiser, and the designated delivery is performed. When the predetermined period has passed until the end of the period, the distribution target of the advertisement may be extended to the target user and distributed. In this way, the delivery unit 136 expands the delivery target of the advertisement by considering the number of remaining impressions of the advertisement and the period until the delivery end, or narrows the target of the original retargeting advertisement. You may perform various advertisement distributions.

[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 showing 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 unit 31 is realized by, for example, a NIC or the like. Then, 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. Then, the web content storage unit 32 stores information about web content (in the embodiment, a web page that configures a shopping mall or the like). 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. Further, the web content storage unit 32 may store information about each store. For example, the web content storage unit 32 may store information about stores that are open in shopping malls, information about products that the stores handle, and the like.

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

  As shown in FIG. 9, the control unit 33 includes a reception unit 34 and a distribution unit 35, and realizes or executes the functions and actions of information processing described below. Note that the internal configuration of the control unit 33 is not limited to the configuration shown in FIG. 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 reception unit 34 receives 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 delivery unit 35 delivers the web page to the user terminal 10 when the reception unit 34 receives the web page acquisition request. Specifically, the distribution unit 35 acquires the web page of the acquisition request target 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 a behavior log such as shopping) related to the behavior performed by the user terminal 10 on the web page to the extraction device 100.

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

  As shown in FIG. 10, the extraction device 100 determines whether or not the submission of an advertisement has been accepted from the first store (step S101). When the submission of the advertisement has not been received (step S101; No), the extraction device 100 waits until the submission of the advertisement is received.

  On the other hand, when the advertisement submission is received from the first store (step S101; Yes), the extraction device 100 acquires the inflow query of the first store (step S102). Then, the extraction device 100 executes a search with the acquired inflow query (step S103).

  Subsequently, the extraction device 100 counts the second upper store of the search result (step S104). Furthermore, 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, a procedure of processing in which the extraction device 100 extracts a target user to whom an advertisement is to be distributed will be described with reference to FIG. 11. FIG. 11 is a flowchart (2) showing the processing procedure according to the embodiment.

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

  On the other hand, when receiving the notification that the advertisement distribution opportunity has occurred (step S201; Yes), the extraction device 100 refers to the access information of the user who has the advertisement distribution opportunity (step S202). Then, the extraction device 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 device 100 extracts the user as a candidate for the delivery destination of the advertisement submitted from the first store (step S204). Furthermore, the extraction device 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 device 100 distributes the advertisement submitted from the first store to the user (step S206).

  Note that when there is no access history to the related store (step S203; No) or when the user does not meet other distribution conditions (step S205; No), the extraction device 100 displays the advertisement selected according to the predetermined condition. It is delivered to the user (step S207). For example, the extraction device 100 selects an advertisement other than the advertisement posted from the first store and has matching distribution conditions among the held advertisements, and distributes the selected advertisement to the user.

[6. Modification example)
The extraction device 100 described above may be implemented in various different forms other than the above embodiment. Therefore, other embodiments of the extraction apparatus 100 will be described below.

[6-1. Store type]
In the above embodiment, the example in which the extraction device 100 specifies the related store of the first store among the stores belonging to one shopping mall has been described. 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 treat each shopping mall scattered throughout the network as a store and execute the process according to the embodiment. Specifically, the extraction device 100 receives an advertisement submitted by the administrator of one shopping mall and identifies another shopping mall related to the one shopping mall. Then, the extraction device 100 may extract a user who has a history of accessing another shopping mall as a target user and deliver the advertisement of the one shopping mall in which the advertisement is submitted to the extracted target user.

  As described above, the store according to the embodiment is merely a conceptual one, 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 it is, the store may have any form.

[6-2. Specification of related store]
The extraction device 100 may explicitly accept the designation of the related store from the advertiser. Specifically, the extraction device 100 receives, from the advertiser, designation of association between the submitted advertisement and a predetermined related store at an arbitrary timing. Then, the extraction device 100 may preferentially deliver the advertisement to users who have accessed the predetermined related store whose designation has been accepted among the target users.

  For example, the extraction device 100 identifies the second store designated by the first store as a conflict store as a 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. 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 specify a predetermined related store and a store to be handled from among the related stores listed.

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

  Accordingly, the extraction device 100 can deliver the targeted advertisement to the customers of the related store that the first store strongly considers 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 embodiment, the extraction device 100 has shown an example of an advertisement regarding a store belonging to a shopping mall or a product handled in the store as the content to be distributed to the user. However, the extraction device 100 may deliver contents other than the store and the product.

  For example, the extraction device 100 may deliver articles such as news and columns as content. Specifically, the extraction device 100 may deliver 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 embodiment, the web page provided by the web server 30 is taken as an example of the 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 or the like included in a predetermined application.

  The advertisement may be displayed together with the result of the search performed by the user. In this way, the extraction device 100 can improve the advertising effect by distributing the advertisement to various media.

[6-5. Use of search results]
In the above-described embodiment, the example in which the extraction device 100 counts the upper second stores of the second stores searched by the inflow query and specifies the related store is described. However, the extraction device 100 does not necessarily need to count the upper second store of the second stores.

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

  As a result, the extraction device 100 may be able to specify the second store, which is more likely to compete with the first store, as the related store. That is, it is highly likely that stores that are closer in rank when searched by the inflow query are similar in business scale, products to be 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 may rank the first store based on the rank of the sales of the product that is the inflow query. The second stores that are close to each other may be counted.

[6-6. Verification of related stores]
The extraction device 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 who access the first store increases as the process according to the embodiment is performed and the advertisement is distributed to users who have no history of accessing the first store. At this time, the extraction device 100 acquires the ratio of users who have converted in both the first store and the related store among the users who have a history of accessing the first store. Then, the extraction device 100 determines that the process that specifies the related store is not an error when the ratio of users who have converted in both the first store and the related store exceeds a predetermined threshold value. On the other hand, the extraction device 100 determines that the process that specifies the relevant store is erroneous when the ratio of the users who have reached the conversion in both the first store and the related store does not exceed the predetermined threshold. Good.

  In other words, the extraction device 100 may determine that the identification as the related store is incorrect because the stores do not conflict with each other when the conversion does not occur in both. In this way, the extraction device 100 can improve the accuracy of the related store identification process by generating feedback of its own process at a predetermined timing.

  In addition, when the number of users who access the first store increases as the advertisement is distributed to users who have no history of accessing the first store, the extraction device 100 detects the advertisement based on a predetermined determination criterion. The delivery method may be changed. For example, when the extraction device 100 determines that the number of users who have a history of access to the first store increases and that a sufficient retargeting advertisement can be delivered, the extraction target is extracted based on the access information to the related store. The advertisement distribution to the user may be interrupted.

[6-7. Identification of related stores based on products]
The extraction device 100 may specify the related store of the first store based on the relationship of the products handled by each store.

  For example, the extraction device 100 acquires the behavior information (purchase history, browsing history, etc.) of the user group in the shopping mall to which the first store belongs. Specifically, the extraction device 100 acquires the behavior information of the user 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 device 100 selects a store that handles the first product as a related store of the first store. Specify. In other words, the extraction device 100 identifies the stores handling the related products as the stores related to each other.

  Here, the extraction device 100 determines the relevance between the first product and the second product based on various determination criteria. As an example, the extraction device 100 identifies the second product from among the arbitrary products based on the number of times or the rate at which the arbitrary product was purchased together with the first product. Specifically, the extraction device 100 identifies, as the second product, the product that is frequently purchased by the user together with the first 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, as the second product, a product purchased by more than a predetermined percentage of the users who purchased the first product at the same time. Alternatively, the extraction device 100 sets a predetermined threshold value in advance, and if the number of times the user who purchased the first product purchases the arbitrary product at the same time exceeds the predetermined threshold value, the extraction device 100 sets the second product as the second product. It may be specified as a product.

  In this case, the extraction device 100 extracts the target user based on the access information for the first product handled by the related store. Specifically, the extraction device 100 extracts, as a target user, 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.

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

  It is estimated that a user who has accessed the first product in the related store is likely to purchase the second product in the related store. Therefore, the extraction device 100 distributes the 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 delivers the advertisement of the second product to the user who is interested in the first product that tends to be purchased together with the second product. As a result, the extraction device 100 can perform advertisement distribution with a higher appealing effect as compared with the case of distributing advertisements to unspecified users. Further, the extraction device 100 can attract the user to the first store by distributing the advertisement of the first store to the user who is going to purchase the second product in the related store.

  The extraction device 100 may use a different method for determining the relevance between the first product and the second product. For example, the extraction device 100 identifies the second product from the arbitrary products based on the number of times or the rate at which the arbitrary user having the history of browsing the first product in the arbitrary store has purchased the desired product. May be. That is, the extraction device 100 may specify, as a second product, a product that is frequently purchased in a user group having a history of browsing the first product, even if the first product is not purchased.

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

[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, for example, a computer 1000 having a configuration illustrated in FIG. Hereinafter, the extraction device 100 will be described as an example. FIG. 12 is a hardware configuration diagram illustrating an example of a computer 1000 that realizes the functions of the extraction device 100. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an 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 starts up, a program dependent on the hardware of the computer 1000, and the like.

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

  The CPU 1100 controls output devices such as a display and a printer and input devices 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. The CPU 1100 also 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 the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the 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 realizes the function of the control unit 130 by executing the program loaded on the RAM 1200. Further, the HDD 1400 stores the 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. Other]
Further, of the processes described in the above embodiment, all or part of the processes described as being automatically performed may be manually performed, or the processes described as being manually performed may be performed. All or part of the process can be automatically performed by a known method. In addition, the processing procedures, specific names, information including various data and parameters shown in the above-mentioned documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various kinds of information shown in each drawing are not limited to the illustrated information.

  Further, each constituent element of each illustrated device is functionally conceptual, and does not necessarily have to be physically configured as illustrated. That is, the specific form of distribution/integration of each device is not limited to that shown in the figure, and all or a part of the device may be functionally or physically distributed/arranged in arbitrary units according to various loads and usage conditions. It 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, the information stored in the storage unit 120 may be stored in a predetermined storage device provided outside via the network N.

  Further, in the above-described embodiment, the example in which the extraction device 100 performs the identification process of identifying the related store and the extraction process of extracting the target user has been described. However, the extraction device 100 described above may be separated into a specific device that performs the specific process and an extraction device that performs the extraction process. In this case, the identifying device includes at least the identifying unit 133. The extraction device has at least an extraction unit 135. Then, the processing by the extraction device 100 described above is realized by the extraction system 1 including each of the identification device and the extraction device.

  Further, the above-described embodiments and modified examples can be appropriately combined within a range in which the processing content is not inconsistent.

[9. effect〕
As described above, the extraction device 100 according to the embodiment has the identification unit 133 and the extraction unit 135. The identifying unit 133 identifies a related store that is a store related to the first store managed by the provider of the predetermined content. The extraction unit 135 extracts a target user who is a candidate for the provision destination of the predetermined content, based on the access information to the related store identified by the identification unit 133.

  As described above, the extraction device 100 according to the embodiment extracts target users who are candidates for the destination of the predetermined content based on the access information to the related store. Also, the provider of the first store can extract the content as the destination of the content desired to be provided. As a result, the extraction device 100 can efficiently expand the distribution target users while maintaining a high content appealing effect.

  Further, the extraction device 100 according to the embodiment further includes an acquisition unit 132 that acquires a query that causes the first store or a product handled by the first store to be output as a search result when input to a predetermined search engine. The identifying unit 133 identifies the related store based on the search result obtained when the query is input to a predetermined search engine.

  In this way, the extraction device 100 according to the embodiment identifies the related store based on the relevance obtained from the search result. As a result, the extraction device 100 can accurately identify a store that may conflict with the first store.

  Further, the acquisition unit 132 acquires the query that triggered 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 the user to access the first store is input to a predetermined search engine.

  In this way, the extraction device 100 according to the embodiment identifies a related store using the search result using the inflow query to the first store. As a result, the extraction device 100 can accurately identify a store that may conflict with the first store.

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

  As described above, the extraction device 100 according to the embodiment identifies 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 to each other, the extraction device 100 can accurately specify a store that is strongly 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 a predetermined order or more among the products searched by the query.

  In this way, the extraction device 100 according to the embodiment may identify the related store based on the sales of the product. As a result, the extraction device 100 can preferentially specify a store having a competitiveness such that it can compete with the first store as a related store.

  In addition, the acquisition unit 132 acquires history information indicating that the user has converted in the related store. The extraction unit 135 extracts the target user based on the number of times or the rate of conversion in the related store.

  As described above, the extraction device 100 according to the embodiment can extract, for example, a user who has a high purchasing will preferentially as a target user by acquiring the history of conversions in the related store. Therefore, the extraction device 100 can extract a user who is expected to have a higher content appealing effect when the content is distributed.

  Further, the identifying unit 133 identifies a store other than the first store as a related store based on history information in which a user having a history of conversion in the first store has reached a conversion in a store other than the first store. To do.

  In this way, the extraction device 100 according to the embodiment may identify the related store based on the conversion between the stores. That is, since the extraction device 100 specifies the related store by various methods as well as the search result of the query, 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 a predetermined product, the identifying unit 133 identifies the store that handles the first product as a related store. The extraction unit 135 extracts the target user based on the access information for the first product handled by the related store.

  In this way, the extraction device 100 according to the embodiment may identify the related store based on the product handled by the store. Accordingly, the extraction device 100 can specify the related store from a multifaceted viewpoint.

  Further, the specifying unit 133 specifies the second product from the arbitrary products based on the number of times or the rate at which the arbitrary product was purchased together with the first product.

  In this way, the extraction device 100 according to the embodiment identifies a product that tends to be purchased with the first product as a second product. As a result, the extraction device 100 can accurately identify stores that are similar to each other as users who are purchasers as related stores.

  Further, the specifying unit 133 specifies the second product from the arbitrary products based on the number of times or the rate at which the arbitrary user having the history of browsing the first product in the arbitrary store purchases the desired product. To do.

  In this way, the extraction device 100 according to the embodiment identifies a product, which has a high tendency to be purchased by a user who browses the first product, as a second product. Thus, the extraction device 100 can specify 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 it has the same or similar product information as the first product or has the model number related to the first product.

  In this way, the extraction device 100 according to the embodiment may specify the second product based on the information set in the product and the like. Thereby, the extraction device 100 can identify the second product based on the similarity of the products themselves, not only by the behavior of the user.

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

  In this way, the extraction device 100 according to the embodiment may extract the user as a distribution target of the content related to the second product handled in the first store (for example, an advertisement promoting the second product). As a result, the extraction device 100 can preferentially extract a user who is expected to have a high appeal effect for the distributed content.

  Further, the extraction device 100 according to the embodiment delivers the reception unit 131 that receives the submission of the 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 device 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.

  Further, the receiving unit 131 receives designation of association between a predetermined content and a predetermined related store from a provider of the predetermined content. The distribution unit 136 preferentially distributes the predetermined content to the user who has accessed the predetermined related store whose designation is received by the reception unit 131 among the target users.

  In this way, the extraction device 100 according to the embodiment may deliver the content based on the access information to the designated related store. As a result, the extraction device 100 can perform the content distribution targeted to the customers of the store that the first store considers as a competition.

  Further, the reception unit 131 receives the designation of the number of distributions for distributing the predetermined content to the user. When the remaining number of the designated distribution number exceeds the predetermined number, the delivery unit 136 delivers the predetermined content to the target user, and the remaining number of the designated delivery number is less than or equal to the predetermined number. In this case, the predetermined content is distributed to users who have a history of accessing the first store.

  In this way, the extraction device 100 according to the embodiment may expand the users who are the distribution destinations based on the remaining number of contents. As a result, the extraction device 100 can perform a distribution process that makes it possible to distribute the content to a greater number of targets and to achieve effective distribution that is limited to retargeting distribution.

  Further, the reception unit 131 receives designation of a distribution period in which predetermined content is distributed to the user. If the predetermined period has not passed until the end of the specified distribution period, the distribution unit 136 distributes the predetermined content to the user who has a history of accessing the first store, and the distribution unit 136 determines whether the specified distribution period is reached. When the predetermined period has passed until the end, the distribution target of the predetermined content is extended to the target user and distributed.

  In this way, the extraction device 100 according to the embodiment may expand the users who are the distribution destinations based on the distribution period. As a result, the extraction device 100 can perform a distribution process that reliably distributes the content in the designated period and effectively distributes the retargeting distribution.

  The embodiments of the present application have been described in detail above with reference to the drawings. However, this is an example, and various modifications and improvements are made based on the knowledge of those skilled in the art, including the modes described in the section of the disclosure of the invention. The present invention can be carried out in other forms described above.

  Also, the above-mentioned "section (module, unit)" can be read as "means" or "circuit". For example, the acquisition unit can be read as an acquisition unit or an acquisition circuit.

1 Extraction System 10 User Terminal 30 Web Server 100 Extraction Device 110 Communication Unit 120 Storage Unit 121 Advertising Information Storage Unit 122 Store Related Information Storage Unit 123 Search Result Table 124 Related Table 125 Access Information Storage Unit 130 Control Unit 131 Receiving Unit 132 Acquisition Unit 133 identification unit 134 reception unit 135 extraction unit 136 distribution unit

Claims (24)

A specifying unit that specifies a related store that is a store related to the first store managed by the provider of the predetermined content and that is a store that opens in the same shopping mall as the shopping mall in which the first store opens;
An extraction unit that extracts a target user who is a candidate for the provision 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
The specifying unit is
A store related to the query acquired by the acquisition unit, and identifies the related store from stores other than the first store,
An extraction device characterized by the above. The acquisition unit is
When a query is input to a predetermined search engine, a query for outputting the first store or a product handled by the first store as a search result is acquired,
The specific unit is
Identifying the relevant store based on search results obtained when the query is entered into a given search engine,
The extraction device according to claim 1 , wherein The acquisition unit is
Obtain the query that triggered the user to access the first store,
The specific unit is
The related store is specified based on a search result obtained when a query that triggers the user to access the first store is input to a predetermined search engine,
The extraction device according to claim 2 , wherein: The specific unit is
A second store that is a store or a product that is output as a search result together with the first store or the first store when the query is input to a predetermined search engine, or a store other than the first store or Specify the related store from the second store based on a product handled by the second store,
The extraction device according to any one of claims 1 to 3, which is characterized in that. The specific unit is
Of the products searched by the query, a second store that handles products whose sales order is a predetermined order or more is specified as the related store.
The extraction device according to claim 4 , wherein: The acquisition unit is
Acquire history information indicating that the user has reached a conversion in the related store,
The extraction unit,
Extracting the target user based on the number or rate of conversions in the related store,
Extraction device according to any one of claims 1 to 5, characterized in that. A specifying unit that specifies a related store that is a store that is related to the first store managed by the provider of the predetermined content and that is a store that opens in the same shopping mall that the first store opens,
An extraction unit that extracts a target user who is a candidate for a destination to which the predetermined content is provided, based on access information to the related store identified by the identification unit;
Equipped with
The specific unit 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 of conversion in a store other than the first store.
An extraction device characterized by the above. A specifying unit that specifies a related store that is a store that is related to the first store managed by the provider of the predetermined content and that is a store that opens in the same shopping mall that the first store opens,
An extraction unit that extracts a target user who is a candidate for a destination to which the predetermined content is provided, based on access information to the related store identified by the identification unit;
Equipped with
The specific unit is
A second product, which is a product related to the first product, is specified from the arbitrary products based on the number of times or the rate at which the arbitrary product was purchased together with the first product, which is a predetermined product, and the second product When the first store handles the product, the store handling the first product is specified as a related store,
The extraction unit,
Extracting the target user based on access information for the first product handled by the related store,
An extraction device characterized by the above. A specifying unit that specifies a related store that is a store related to the first store managed by the provider of the predetermined content and that is a store that opens in the same shopping mall as the shopping mall in which the first store opens;
An extraction unit that extracts a target user who is a candidate for a destination to which the predetermined content is provided, based on access information to the related store identified by the identification unit;
Equipped with
The specific unit is
An arbitrary user having a history of browsing a first product which is a predetermined product in an arbitrary store is related to the first product among the arbitrary products based on the number of times or the ratio of purchasing the arbitrary product. When a second product that is a product is identified and the first product handles the second product, the store that handles the first product is identified as a related store,
The extraction unit,
Extracting the target user based on access information for the first product handled by the related store,
An extraction device characterized by the above. The specifying unit is
The second product is specified based on whether it has the same or similar product information as the first product or has a model number related to the first product.
The extraction device according to claim 8 or 9 , characterized in that. The extraction unit,
Extracting the target user as a candidate for a destination of content related to the second product, based on access information for the first product handled by the related store,
The extraction device according to any one of claims 8 to 10 , characterized in that. A specifying unit that specifies a related store that is a store that is related to the first store managed by the provider of the predetermined content and that is a store that opens in the same shopping mall that the first store opens,
An extraction unit that extracts a target user who is a candidate for a destination to which the predetermined content is provided, based on access information to the related store identified by the identification unit;
A reception unit that receives the submission of the predetermined content,
A distribution unit that distributes the predetermined content accepted by the acceptance unit to the target users extracted by the extraction unit;
Equipped with
The reception unit is
Accept the specification of the number of distribution of the predetermined content to the user,
The delivery unit is
When the remaining number of the designated delivery number exceeds a predetermined number, the predetermined content is delivered to the target user, and when the remaining number of the designated delivery number is less than or equal to the predetermined number. Distributing the predetermined content to a user who has a history of accessing the first store,
An extraction device characterized by the above. The reception unit is
The designation of the association between the predetermined content and the predetermined related store is accepted from the provider of the predetermined content,
The delivery unit is
Of the target users, the predetermined content is preferentially distributed to a user who has accessed a predetermined related store whose designation has been received by the reception unit,
The extraction device according to claim 12 , wherein: The reception unit is
Accept the specification of the distribution period to distribute the predetermined content to the user,
The delivery unit is
When the specified period of time has not passed until the end of the specified distribution period, the specified content is distributed to the user who has a history of accessing the first store, and the specified period of time ends until the specified distribution period ends. If it passes, the delivery target of the predetermined content is extended to the target user and delivered,
The extraction device according to claim 12 or 13 , characterized in that. A computer-implemented extraction method,
A specifying step of specifying a related store which is a store related to the first store managed by the provider of the predetermined content and which is a store that opens in the same shopping mall as the shopping mall in which the first store opens;
An extraction step of extracting a target user who is a candidate for the provision destination of the predetermined content, based on access information to the related store identified by the identification step;
An acquisition step of acquiring a query related to the first store or a product handled by the first store;
Including,
The specific step is
A store related to the query acquired in the acquisition step, and specifying the related store from stores other than the first store,
An extraction method characterized by the above. A specific procedure for identifying a related store which is a store related to a first store managed by a provider of predetermined content and which is a store that opens in the same shopping mall as the shopping mall in which the first store opens,
An extraction procedure for extracting a target user who is a candidate for the provision 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 run on your computer,
The specific procedure is
A store related to the query acquired by the acquisition procedure, the store being specified from among stores other than the first store,
An extraction program characterized by that. A computer-implemented extraction method,
A specifying step of specifying a related store which is a store related to the first store managed by the provider of the predetermined content and which is a store that opens in the same shopping mall as the shopping mall in which the first store opens;
An extraction step of extracting a target user who is a candidate for the provision destination of the predetermined content, based on access information to the related store identified by the identification step;
Including,
The specific step 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 of conversion in a store other than the first store.
An extraction method characterized by the above. A specific procedure for identifying a related store which is a store related to a first store managed by a provider of predetermined content and which is a store that opens in the same shopping mall as the shopping mall in which the first store opens,
An extraction procedure for extracting a target user who is a candidate for the provision destination of the predetermined content, based on access information to the related store identified by the identification procedure;
To run on your computer,
The specific procedure 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 of conversion in a store other than the first store.
An extraction program characterized by that. A computer-implemented extraction method,
A specifying step of specifying a related store which is a store related to the first store managed by the provider of the predetermined content and which is a store that opens in the same shopping mall as the shopping mall in which the first store opens;
An extraction step of extracting a target user who is a candidate for the provision destination of the predetermined content, based on access information to the related store identified by the identification step;
Including,
The specific step is
A second product, which is a product related to the first product, is specified from the arbitrary products based on the number of times or the rate at which the arbitrary product was purchased together with the first product, which is a predetermined product, and the second product When the first store handles the product, the store handling the first product is specified as a related store,
The extraction step is
Extracting the target user based on access information for the first product handled by the related store,
An extraction method characterized by the above. A specific procedure for identifying a related store which is a store related to a first store managed by a provider of predetermined content and which is a store that opens in the same shopping mall as the shopping mall in which the first store opens,
An extraction procedure for extracting a target user who is a candidate for the provision destination of the predetermined content, based on access information to the related store identified by the identification procedure;
To run on your computer,
The specific procedure is
A second product, which is a product related to the first product, is specified from the arbitrary products based on the number of times or the rate at which the arbitrary product was purchased together with the first product, which is a predetermined product, and the second product When the first store handles the product, the store handling the first product is specified as a related store,
The extraction procedure is
Extracting the target user based on access information for the first product handled by the related store,
An extraction program characterized by that. A computer-implemented extraction method,
A specifying step of specifying a related store which is a store related to the first store managed by the provider of the predetermined content and which is a store that opens in the same shopping mall as the shopping mall in which the first store opens;
An extraction step of extracting a target user who is a candidate for the provision destination of the predetermined content, based on access information to the related store identified by the identification step;
Including,
The specific step is
An arbitrary user having a history of browsing a first product which is a predetermined product in an arbitrary store is related to the first product among the arbitrary products based on the number of times or the ratio of purchasing the arbitrary product. When a second product that is a product is identified and the first product handles the second product, the store that handles the first product is identified as a related store,
The extraction step is
Extracting the target user based on access information for the first product handled by the related store,
An extraction method characterized by the above. A specific procedure for identifying a related store which is a store related to a first store managed by a provider of predetermined content and which is a store that opens in the same shopping mall as the shopping mall in which the first store opens,
An extraction procedure for extracting a target user who is a candidate for the provision destination of the predetermined content, based on access information to the related store identified by the identification procedure;
To run on your computer,
The specific procedure is
An arbitrary user having a history of browsing a first product which is a predetermined product in an arbitrary store is related to the first product among the arbitrary products based on the number of times or the ratio of purchasing the arbitrary product. When a second product that is a product is identified and the first product handles the second product, the store that handles the first product is identified as a related store,
The extraction procedure is
Extracting the target user based on access information for the first product handled by the related store,
An extraction program characterized by that. A computer-implemented extraction method,
A specifying step of specifying a related store which is a store related to the first store managed by the provider of the predetermined content and which is a store that opens in the same shopping mall as the shopping mall in which the first store opens;
An extraction step of extracting a target user who is a candidate for a destination of provision of the predetermined content based on access information to the related store identified by the identification step;
A receiving step of receiving the submission of the predetermined content,
A distribution step of distributing the predetermined content accepted by the acceptance step to the target users extracted by the extraction step,
Including,
The reception process is
Accept the specification of the number of distribution of the predetermined content to the user,
The delivery process is
When the remaining number of the designated delivery number exceeds a predetermined number, the predetermined content is delivered to the target user, and when the remaining number of the designated delivery number is less than or equal to the predetermined number. Distributing the predetermined content to a user who has a history of accessing the first store,
An extraction method characterized by the above. A specific procedure for identifying a related store which is a store related to a first store managed by a provider of predetermined content and which is a store that opens in the same shopping mall as the shopping mall in which the first store opens,
An extraction procedure for extracting a target user who is a candidate for the provision destination of the predetermined content, based on access information to the related store identified by the identification procedure;
A reception procedure for receiving the submission of the predetermined content,
A delivery procedure for delivering the predetermined content accepted by the acceptance procedure to target users extracted by the extraction procedure;
To run on your computer,
The reception procedure is
Accept the specification of the number of distribution of the predetermined content to the user,
The delivery procedure is
When the remaining number of the designated delivery number exceeds a predetermined number, the predetermined content is delivered to the target user, and when the remaining number of the designated delivery number is less than or equal to the predetermined number. Distributing the predetermined content to a user who has a history of accessing the first store,
An extraction program characterized by that.

Images