JP2018088282A - Extracting apparatus, extracting method, and extracting program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve accuracy in extracting content with high appealing effect.SOLUTION: An extracting apparatus according to the present invention has an acquiring unit and an extracting unit. The acquiring unit acquires, in commerce transaction service provided through a communication network, an action history of a user indicating result for whether or not the user has purchased a specific commercial object, among information relating to the user. The extracting unit extracts, based on the user action history acquired by the acquiring unit, predetermined content to be distributed to the user. For example, the extracting unit extracts the predetermined content to be distributed to the user, on the basis of information extracted from the user action history and the content information set with respect to the content.SELECTED DRAWING: Figure 1

Description

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

  In recent years, with the rapid spread of the Internet, advertisement distribution based on information acquired via a network is actively performed. In such advertisement distribution, in order to enhance the advertising effect, user information such as user preference, gender, age, address, occupation, etc. is registered in advance, and the advertisement corresponding to the user information is selectively distributed Delivery is taking place.

  For example, as an example of advertisement distribution utilizing the user information as described above, a technology related to a direct mail system (hereinafter referred to as Conventional Technology 1) that can deliver product information that motivates customers to purchase in a timely manner. Is known). Further, based on a search query transmitted from the user, even if the purchase history is not used, it is determined whether or not the user's situation is the purchase stage, and an advertisement is sent to the user who is determined to be the purchase stage. A technique for distribution (hereinafter referred to as conventional technique 2) is known.

JP 2004-206415 A JP2011-118759A

  However, with the above-described conventional technology, it has been difficult to improve the accuracy of extracting content with a high appealing effect. Specifically, the above-described prior art 1 merely sends a direct mail to each user based on the personal information and purchase history of the user who has purchased the product. For relatively few users, the content to be transmitted cannot be appropriately extracted. Further, the above-described conventional technique 2 merely estimates whether or not the user is in the purchase stage based on the search query, and it is not certain whether the distributed content and the user are appropriately matched. That is, a user who is a distribution target of an advertisement is not necessarily highly motivated to purchase a product or the like presented in the distributed advertisement, and may not be able to sufficiently exert the advertising appeal effect.

  In the above description, the content related to the advertisement is taken as an example of content, and it has been described that it is difficult to improve the accuracy of extracting content with a high appeal effect. However, in the case of content other than the content related to the advertisement, it is not always possible to improve the accuracy of extracting content with a high appeal effect. In other words, the present invention is not limited to the example of advertisement delivery as described above, and in the technical field of delivering content using user information, if user information is not properly utilized, content with a high appealing effect can be accurately extracted. Have difficulty.

  The present application has been made in view of the above, and an object thereof is to provide an extraction device, an extraction method, and an extraction program capable of improving the accuracy of extracting content having a high appeal effect.

  The extraction device according to the present application includes an acquisition unit that acquires an action history indicating a result of whether or not a specific product has been purchased from a user in a commercial transaction service provided through a communication network among information about the user; And an extraction unit that extracts predetermined content distributed to the user based on the user's behavior history acquired by the acquisition unit.

  According to one aspect of the embodiment, there is an effect that it is possible to improve the accuracy of extracting content with a high appeal effect.

FIG. 1 is a diagram illustrating an example of an extraction process according to the embodiment. FIG. 2 is a diagram illustrating a configuration example of the extraction processing system according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of the advertising device according to the embodiment. FIG. 4 is a diagram illustrating an example of the advertisement information storage unit according to the embodiment. FIG. 5 is a diagram illustrating an example of the behavior information storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of the feature information storage unit according to the embodiment. FIG. 7 is a diagram illustrating a configuration example of the auction server according to the embodiment. FIG. 8 is a diagram illustrating an example of a product information storage unit according to the embodiment. FIG. 9 is a sequence diagram illustrating an example of an extraction processing procedure performed by the extraction processing system according to the embodiment. FIG. 10 is a flowchart illustrating a generation processing procedure performed by the advertising device according to the embodiment. FIG. 11 is a flowchart illustrating an extraction processing procedure by the advertising device according to the embodiment. FIG. 12 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the advertising device.

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

[1. (Outline of extraction process)
First, an example of the extraction process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of an extraction process according to the embodiment. FIG. 1 shows an example in which an advertisement content distributed to a user is extracted by an advertisement device 100 corresponding to the extraction device according to the present application.

  The advertising device 100 performs appropriate matching processing between the user who is the distribution target and the advertisement content to be distributed, by using information about the user (hereinafter referred to as “user information”). In other words, the advertising device 100 extracts advertising content that is expected to increase the advertising effect by being distributed to a specific user, and distributes the extracted advertising content to the user. Advertisers who request advertisement distribution use the advertising device 100, and advertisement contents that are highly likely to be able to obtain some result from the user when advertisement distribution is triggered, and advertisement contents that are expected to increase the click rate That is, the distribution of advertising content with a high advertising effect is realized.

  The user information means that the user terminal 10, which is an information processing terminal operated by a general user, accesses the website (transmits information indicating that a banner advertisement has been clicked on the web page, or purchases a product on the shopping page. Log data (in other words, a user's action history) and the like. In this specification, user information related to such an action history may be referred to as “behavior information”. In addition, the user information includes user's own attribute information (for example, the user's age, sex, preference, etc.) derived from the website access history, purchase history, and the like.

  In the example of FIG. 1, the advertising device 100 according to the embodiment acquires user information including user behavior information and uses it for the extraction processing of advertising content. In addition, the advertising device 100 uses the behavior information corresponding to the purchase stage (bidding, successful bid, etc.) of the user at the auction site among the user behavior information, and executes the advertising content extraction process. Below, the outline | summary of the extraction process of the advertising content performed by the advertising device 100 is demonstrated along a flow.

  As shown in FIG. 1, the user terminal 10 accesses the auction site (step S11). The auction site is provided by an auction server 30 that is a server device that manages the auction site. That is, the user terminal 10 accesses the auction server 30 and uses an auction site provided by the auction server 30. When the user terminal 10 accesses the auction site, the user terminal 10 appropriately acquires a web page that forms the auction site.

  When accessing the auction server 30, the user terminal 10 sends an HTTP cookie (HyperText Transfer Protocol Cookie: hereinafter simply referred to as “cookie”), which is information transmitted and received between the web browser and the server, to the auction server. 30. As a result, the service content used by the user terminal 10 in the auction site and behavior information such as bids and successful bids on products are stored in the auction server 30. Note that the user terminal 10 can hold an action history in the auction site by transmitting and receiving a cookie every time the auction server 30 is accessed. Moreover, since the auction server 30 can identify the user terminal 10 by the cookie transmitted from the user terminal 10, it can provide a service based on the behavior information of the user terminal 10 at every access. Here, the cookie is stored in correspondence with the web browser of the user terminal 10. For this reason, even when the user terminal 10 accesses a web server other than the auction server 30, the action information on the auction server 30 can be used on other websites by transmitting and receiving cookies.

  The auction server 30 acquires behavior information of the user terminal 10 in the auction site (step S12). Then, the auction server 30 transmits the acquired behavior information of the user terminal 10 to the advertising device 100 (step S13). Advertising device 100 accumulates action information acquired from auction server 30 (Step S14). Then, the advertising device 100 generates feature information corresponding to each user terminal 10 based on the accumulated behavior information (step S15).

  As will be described in detail later, the advertising device 100 acquires, as user action information, an action history in which an item is registered by a user as a candidate for purchase on an auction site. For example, the advertising device 100 may include an action history in which a product is registered as a candidate for purchase, an action in which a user bids for a specific product, an action in which a specific product is registered in a watch list as a bid candidate product, As a result, an action history such as an action of making a successful bid for a specific product is acquired. Then, the advertising device 100 generates feature information for each user terminal 10 based on a product name such as a product bid on the auction site, a product name registered in the watch list, or a keyword extracted from the product category. Then, the advertising device 100 stores the generated feature information for each user terminal 10. Note that the watch list is a service function for listing products selected by the user in order to confirm trends in future auctions. In other words, the product registered in the watch list is a candidate product for which the user bids in the future.

  Thereafter, the user terminal 10 accesses a predetermined portal site (step S16). A portal site is a website that provides various services such as search engines, news articles, and mail services. Here, the predetermined portal site is provided by the web server 40. The portal site includes a predetermined advertisement space. The user terminal 10 accesses the web server 40 to obtain a web page that configures the portal site from the web server 40. When the user terminal 10 tries to display the portal site on the web browser, the user terminal 10 transmits a request for distributing the advertising content to be displayed in the advertising space to the advertising device 100 (step S17).

  The advertising device 100 acquires information for identifying the user terminal 10 together with the advertisement distribution request transmitted from the user terminal 10. For example, the advertising device 100 receives a cookie from the user terminal 10 and identifies the user terminal 10.

  Then, the advertising device 100 selects the advertising content to be distributed to the user terminal 10 based on the characteristic information corresponding to the user terminal 10 that requested the advertisement distribution among the characteristic information held. In other words, the advertising device 100 extracts advertising content corresponding to the user who operates the user terminal 10 (step S18). In this case, the advertising device 100 performs tagging to explain the feature information of the user terminal 10 generated based on the behavior information, the category of the advertising content set in advance when the advertising content is submitted, and the advertising content. The advertisement content to be distributed is extracted by calculating the similarity to the content information based on the keyword (hereinafter, sometimes referred to as “advertisement keyword”). For example, the advertising device 100 extracts the advertising content having the highest similarity between the feature information and the content information as a delivery candidate. Then, the advertising device 100 distributes the extracted advertising content to the user terminal 10 that has transmitted the advertisement distribution request (step S19).

  As described above, the advertising device 100 according to the embodiment is specific to a user in a commercial transaction service (for example, a website that provides a commercial transaction service such as an auction site) provided through a communication network among information about the user. An action history in which merchandise (for example, a product that can be purchased on a website or a service that is the object of a commercial transaction) is registered as a candidate for purchase is acquired. Then, the advertising device 100 extracts advertising content distributed to the user based on the acquired user behavior history.

  In other words, the advertising device 100 according to the embodiment performs actions such as bidding on a commercial transaction site such as an auction site in addition to user attribute information, user website browsing information, and the like that are used in general targeting advertisements. Advertising content is extracted using information extracted from the history. Here, for a user, a product that is bid on an auction site or registered in a watch list as a bid candidate (that is, a product that is registered in the auction site as a candidate for purchase) is simply a product or the like that browses a shopping site. In comparison, it can be said that the product has a high user's willingness to purchase and is highly interested. In addition, in the auction site, since a period during which a product can be bid and a successful bid time (transaction end time) are determined, it is assumed that the user's interest in the product is higher during the period in which the transaction is performed. The advertising device 100 acquires user behavior information on such an auction site, and based on information including the user behavior stage (for example, bidding, successful bid, registration as a bid candidate, etc.) Therefore, it is possible to improve the accuracy of extracting advertising content having a high appeal effect in accordance with the user's interests. As a result, the advertising device 100 delivers the extracted appropriate advertising content to users who are likely to reach conversion (Conversion) and users who are likely to have high CTR (Click Through Rate). Therefore, it can be expected to improve the advertisement effect by advertisement distribution.

  1 shows an example in which the auction server 30 transmits user behavior information to the advertising device 100 in step S13. Moreover, in step S17, the user terminal 10 showed the example which transmits the identification information of the user terminal 10 to the advertising apparatus 100 with the request | requirement of advertisement delivery. However, transmission / reception of information as described above may be realized by a web beacon or the like.

  That is, the web page provided by the auction server 30 and the web server 40 may be embedded with a notification function related to user information realized by a web beacon or the like. For example, the web beacon has a function of allowing the user terminal 10 that has accessed the web page to access a transparent image or a very small image (sometimes referred to as “clear GIF”) stored in the advertising device 100. Thereby, the advertising device 100 can receive and acquire user information from the user terminal 10. For example, the advertising device 100 may receive a cookie from the user terminal 10 that has accessed the auction server 30 by a function realized by a web beacon. Further, the advertising device 100 may receive a cookie from the user terminal 10 that has accessed the web server 40. Then, the advertising device 100 acquires user information based on the received cookie.

[2. Configuration of extraction processing system)
Next, the configuration of the extraction processing system 1 including the advertising device 100 according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating a configuration example of the extraction processing system 1 according to the embodiment. As illustrated in FIG. 2, the extraction processing system 1 according to the embodiment includes a user terminal 10, an advertiser terminal 20, an auction server 30, a web server 40, and an advertising device 100. These various apparatuses are communicably connected via a network N (for example, a communication network such as the Internet) in a wired or wireless manner. The extraction processing system 1 shown in FIG. 2 may include a plurality of user terminals 10, a plurality of advertiser terminals 20, a plurality of auction servers 30, and a plurality of web servers 40. Good.

  The user terminal 10 is, for example, an information processing apparatus such as a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, or a PDA (Personal Digital Assistant). For example, the user terminal 10 accesses the auction server 30 or the web server 40 to acquire a web page from a website provided by the auction server 30 or the web server 40, and displays the acquired web page on a display device ( For example, it is displayed on a liquid crystal display.

  The advertiser terminal 20 is an information processing device used by an advertiser who requests the advertising device 100 to distribute an advertisement. The advertiser terminal 20 submits advertising content to the advertising device 100 in accordance with an operation by the advertiser. In addition, the advertiser terminal 20 sets a category for the advertising content or designates an advertising keyword to be tagged to the advertising content in order to distribute the advertising content to an appropriate distribution target. For example, the advertising device 100 determines an appropriate distribution target based on content information such as a category set for the advertising content and an advertising keyword.

  Note that the advertiser uses the advertiser terminal 20 to request the agency to submit the advertising content without submitting the advertising content to the advertising device 100 or setting a category for the advertising content. In some cases. In this case, it is the agency that submits the advertising content to the advertising device 100. In the following, the term “advertiser” is a concept that includes not only the advertiser but also the agency, and the term “advertiser terminal” includes the agency device used by the agency as well as the advertiser terminal. It is assumed to be a concept.

  The auction server 30 is a server device that provides a web page related to an auction site when accessed from the user terminal 10. The auction server 30 accepts a request for purchasing a product at the auction site from the user terminal 10 and provides various services related to the auction.

  The web server 40 is a server device that provides various web pages when accessed from the user terminal 10. The web server 40 provides various web pages related to, for example, a news site, a weather forecast site, a shopping site, a finance (stock price) site, a route search site, a map providing site, a travel site, a restaurant introduction site, and a web blog.

  The web page distributed by the web server 40 includes an advertisement frame for displaying advertisement content. The web page including the advertisement space includes an advertisement acquisition command for acquiring advertisement content to be displayed in the advertisement space. For example, in an HTML (HyperText Markup Language) file that forms a web page, the URL of the advertising device 100 is described as an advertisement acquisition command. In this case, the user terminal 10 receives the distribution of the advertising content from the advertising device 100 by accessing a URL described in an HTML file or the like.

  As described above, the advertising device 100 uses the user information to extract the advertising content that is expected to have a high advertising effect for the user who requested the advertisement distribution, and the advertising content of the extracted advertising content An information processing apparatus that performs distribution.

  In addition, the advertising device 100 identifies the user terminal 10 and specifies the user terminal 10 that distributes the advertising content when distributing the advertising content. As described in FIG. 1, the user can be identified by including user identification information in a cookie exchanged between the web browser of the user terminal 10 and the advertising device 100. However, the method for identifying the user is not limited to the above. For example, a dedicated program may be set in the user terminal 10 and user identification information may be transmitted to the advertising device 100 from the dedicated program.

[3-1. Configuration of advertising device]
Next, the configuration of the advertising device 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram illustrating a configuration example of the advertising device 100 according to the embodiment. As illustrated in FIG. 3, the advertising device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The advertising device 100 includes an input unit (for example, a keyboard and a mouse) that receives various operations from an administrator who uses the advertising device 100, and a display unit (for example, a liquid crystal display) that displays various types of information. You may have.

(About the communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to the network N by wire or wirelessly, and transmits / receives information to / from the user terminal 10, the advertiser terminal 20, the auction server 30, and the web server 40 via the network N. .

(About the storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 includes an advertisement information storage unit 121, a behavior information storage unit 122, and a feature information storage unit 123.

(Regarding the advertisement information storage unit 121)
The advertisement information storage unit 121 stores information related to advertisement content submitted from the advertiser terminal 20. The advertisement information storage unit 121 stores an advertisement content category and an advertisement keyword set by the advertiser in association with the submitted advertisement content. Here, FIG. 4 illustrates an example of the advertisement information storage unit 121 according to the embodiment. In the example illustrated in FIG. 4, the advertisement information storage unit 121 includes items such as “advertiser ID”, “advertisement content ID”, “advertisement category”, and “advertisement keyword”.

  The “advertiser ID” indicates identification information for identifying the advertiser or the advertiser terminal 20. The “advertisement content ID” indicates identification information for identifying the advertisement content submitted to the advertising device 100 from the advertiser.

  Note that the advertisement content data that is actually distributed to the user terminal 10 may be stored in a predetermined advertisement distribution server provided separately from the advertising device 100. In this case, the advertising device 100 identifies the advertising content stored in the external advertising distribution server based on the advertising content ID stored in the advertising information storage unit 121. Then, the advertising device 100 controls the advertisement distribution server to distribute the specified advertisement content to the user terminal 10.

  In the following, the identification information stored in the advertiser ID and the advertisement content ID shown in FIG. 4 may be used as a reference code for the advertiser and the advertisement content. For example, the advertiser identified by the advertiser ID “CL11” may be referred to as “advertiser CL11”, or the advertisement content identified by the advertisement content ID “AD11” may be denoted as “advertisement content AD11”.

  “Advertisement category” indicates a category of advertisement content. The advertiser designates an advertisement category for classifying the advertisement content when submitting the advertisement content. The advertisement category may not be set by the advertiser. For example, the advertising device 100 may automatically set the advertising category based on the advertising content indicated by texts and images included in the submitted advertising content.

  “Advertising keyword” indicates a keyword to be tagged to the advertising content. The advertisement content is characterized by the advertisement keyword. In other words, the advertising keyword is a keyword that describes the advertising content, and is referred to when the advertising content is extracted as a distribution target. In FIG. 4, the description tagged with the advertisement content is shown by the advertisement keyword. However, the information describing the feature of the advertisement content is not in a format represented by a word like a keyword, but describes the advertisement content. It may be an explanatory text for

  For example, FIG. 4 shows an example in which the advertiser identified by the advertiser ID “CL11” has submitted the advertising content identified by the advertising content ID “AD11”. Further, an example is shown in which the advertiser CL11 designates “automobile” as the advertisement category and “car, drive, vehicle, travel, holiday,...” As the advertisement keyword for the advertisement content AD01.

(About the behavior information storage unit 122)
The behavior information storage unit 122 stores user behavior information acquired by the advertising device 100. Specifically, the behavior information storage unit 122 accesses the auction server 30 when the user terminal 10 accesses the auction server 30, the behavior history of bidding for a product on the auction site, the behavior history of registering the product in the watch list, and the successful bid for the product. Memorized action history and the like.

  Here, FIG. 5 illustrates an example of the behavior information storage unit 122 according to the embodiment. FIG. 5 is a diagram illustrating an example of the behavior information storage unit 122 according to the embodiment. In the example illustrated in FIG. 5, the behavior information storage unit 122 includes items such as “user ID” and “behavior information”, and the “behavior information” items include “purchase stage”, “purchase target”, “ "Action date and time".

  “User ID” is identification information for identifying the user terminal 10. In FIG. 5, the user ID is expressed as “U11”. This indicates that the user terminal 10 is identified by the user ID “U11”. Note that the user ID matches the reference code of the user who operates the user terminal 10. That is, the behavior information corresponding to “user ID = U11” indicates information regarding the behavior performed by the user terminal 10 operated by the user U11.

  “Behavior information” indicates the behavior information of the user (that is, the user terminal 10). “Purchase stage” indicates the stage of purchase by the user (stage until purchase such as bidding or successful bid) in the action information in the auction site. “Purchase target” is information indicating a purchase target on a website, such as a product bid by a user for purchase (purchase). In the example of FIG. 5, an example in which the name of a product for which a bid is made is described in the item to be purchased. “Action date and time” indicates the date and time when the action was performed.

  For example, in FIG. 5, in the auction site, the user terminal 10 identified by the user ID “U11” registers the product “AAA” in the watch list at “2014/09/10 18:30” The product “BBB” was registered in the watch list on September 10, 18:35, and the product “CCC” was registered in the watch list on “September 10, 2014, 18:40”. . The user terminal 10 identified by the user ID “U11” has bid for the product “AAA” on “September 11, 2014, 20:00”. Further, it is indicated that the user terminal 10 identified by the user ID “U11” has made a successful bid for the product “AAA” on “September 13, 2014, 10:00”.

  Although omitted from FIG. 5, the behavior information storage unit 122 stores the user's own attribute information derived from the website access history, purchase history, etc. (for example, the user's age, sex, and preferences). ) Etc. may be included. The behavior information storage unit 122 may store a device ID that is information for identifying the user terminal 10 itself. Unlike the user ID, the device ID indicates identification information recorded in the terminal device itself.

  Further, the behavior information storage unit 122 does not exist inside the advertising device 100, and may be a predetermined log storage server connected to the outside, for example. In this case, the acquisition unit 132 described later can acquire a log stored in a predetermined log storage server via the network N. The advertising device 100 requires a large amount of storage capacity for storing data related to user information when acquiring user information at any time. Here, the advertising device 100 can satisfy the storage capacity requirement by using an external log storage server corresponding to the behavior information storage unit 122.

(About the feature information storage unit 123)
The feature information storage unit 123 stores feature information for each user terminal 10. Here, FIG. 6 illustrates an example of the feature information storage unit 123 according to the embodiment. In the example illustrated in FIG. 6, the feature information storage unit 123 includes items such as “user ID” and “feature information”.

  “User ID” corresponds to the item of user ID shown in FIG. “Characteristic information” is information generated based on the behavior information for each user terminal 10 and indicates the characteristics of the user terminal 10.

  In the example shown in FIG. 6, the feature information is conceptually expressed as “F11”. However, in practice, the feature information is expressed by a combination of a keyword extracted based on user behavior information and an index value set for each keyword. As an example, the feature information is expressed by a word vector weighted by an index value calculated for each keyword, with the presence or absence of the keyword as an element. Specifically, the user feature information is an element (a vector is expressed by “1” when a predetermined keyword extracted based on the user behavior information is present, and “0” when there is no predetermined keyword. , Dimensions), and is expressed as a word vector composed of elements multiplied (ie, weighted) by the index value calculated for each keyword.

  For example, in FIG. 6, “F11” is generated as feature information in the user terminal 10 identified by the user ID “U11”, and the user ID “U11” and the feature information “F11” are stored correspondingly. Indicates that

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

  As shown in FIG. 3, the control unit 130 includes a submission receiving unit 131, an acquisition unit 132, a generation unit 133, a request reception unit 134, an extraction unit 135, and a distribution unit 136. Implement or execute the functions and operations of the information processing described. Note that the internal configuration of the control unit 130 is not limited to the configuration illustrated in FIG. 3, and may be another configuration as long as the information processing described below is performed. Further, the connection relationship between the processing units included in the control unit 130 is not limited to the connection relationship illustrated in FIG. 3, and may be another connection relationship.

(About the submission acceptance part 131)
The submission accepting unit 131 accepts submission of advertising content from the advertiser terminal 20. For example, the submission receiving unit 131 receives, from the advertiser terminal 20, submission of advertisement content in which an advertisement category and an advertisement keyword are set. Then, the submission receiving unit 131 stores information related to the submitted advertisement content in the advertisement information storage unit 121 in association with the advertiser ID that identifies the advertiser of the submission source.

  The submission receiving unit 131 does not necessarily need to receive the advertisement category and the advertisement keyword simultaneously with the submission of the advertisement content. That is, the submission accepting unit 131 may accept the setting of the advertisement category and the advertisement keyword after submission of the advertisement content, or may accept the change of the setting after accepting the setting of the advertisement category and the advertisement keyword. Good.

(About the acquisition unit 132)
The acquisition unit 132 acquires information about the user. For example, the acquisition unit 132 registers a specific product as a candidate for purchase by the user in the auction site based on the action log of the user terminal 10 transmitted from the auction server 30 as an example of information about the user. Get the action history.

  Specifically, the acquisition unit 132, as user action information (behavior history), an action that a user bids on a specific product or an action that registers a specific product in a watch list as a bid candidate product on an auction site. Get information about. In addition, after the acquisition unit 132 registers a specific product as a candidate for purchase in the auction site, as a result, the acquisition unit 132 acquires information on an action that has acquired the right to purchase the product (that is, a successful bid for the product).

  As shown in FIG. 5, the user behavior information includes a user ID and behavior information related to a predetermined behavior history. The user behavior information shown in FIG. 5 shows an example in which the behavior information of the user terminal 10 in the auction site is described, but the information acquired by the acquisition unit 132 is not limited to such information. For example, the acquisition unit 132 may be access information to websites other than the auction site as user behavior information, search behavior performed by inputting a search query on a search site, purchase behavior on a shopping page, or the like. The user's behavior information may be acquired.

  Further, as described above, the log acquired by the acquisition unit 132 includes a user ID. Therefore, the acquisition unit 132 may acquire, as user information, information related to a user attribute included in user identification information such as a cookie based on the user ID. The acquisition unit 132 may acquire user information by tracking past access information of the user included in the cookie based on the user ID. For example, the acquisition unit 132 can acquire information such as the user's age, sex, interest, and residential area as the user information.

(About the generator 133)
The generation unit 133 generates feature information indicating user characteristics based on the keywords extracted from the user behavior history acquired by the acquisition unit 132. Specifically, the generation unit 133 is based on a keyword extracted from an action history registered as a candidate for purchase on a website providing a commercial transaction service such as an auction site among user information. Then, feature information indicating the feature of the user is generated.

  For example, the generation unit 133 is information included in an action history in which a specific product is registered as a purchase target candidate among the user action histories acquired by the acquisition unit 132, and the process until the user makes a purchase. User characteristic information is generated using information indicating the stage. Specifically, the generation unit 133 uses at least one of information indicating a bid for a product on the auction site, a successful bid for the product, and registration of a bid candidate as information indicating a stage until the user makes a purchase. , Generating user feature information.

  The generation unit 133 sets a predetermined index value for each keyword extracted from the user's behavior history, and generates user feature information weighted by the set index value. As described above, the advertising device 100 extracts the advertising content by calculating the similarity between the user feature information generated by the generating unit 133 and the content information included in the advertising content. For this reason, it is desirable that the generation unit 133 generates feature information that appropriately indicates the user's features. Therefore, the generation unit 133 calculates a predetermined index value for the keyword extracted from the behavior information, which is an element that generates feature information, and weights the calculated index value. Specifically, the generation unit 133 increases the weight of the keyword in the feature information by calculating a relatively high index value for the keyword that is assumed to exhibit more user characteristics.

  For example, the generation unit 133 sets a predetermined index value for each keyword extracted from the user's behavior history, and bids for products on the auction site or registration of bid candidates (for example, registration in a watch list). The keyword extracted from the action history corresponding to is set to a higher index value than the keyword extracted from the action history corresponding to the successful bid of the product, and the user's action weighted by the set index value The feature information of the user is generated using the information. Here, it is assumed that the user has a relatively high willingness to purchase the bid item or the item registered as the bid candidate. Moreover, since the user has already acquired the product for the successful bid product, it is assumed that the user's willingness to purchase is relatively lowered. That is, the generation unit 133 calculates an index value corresponding to such information regarding the purchase stage, and sets a different index value for each keyword extracted from the behavior information. Accordingly, the generation unit 133 generates user feature information based on not only information such as product names that the user is expected to be interested in, but also behavior information that takes into account the user's interest in the purchase stage. be able to.

  Further, the generation unit 133 sets an index value so that a keyword extracted from the latest information in the user's behavior history has a higher numerical value, and generates user feature information weighted by the set index value. . For example, it is assumed that a user who performs a purchasing activity at an auction site or the like shows an interest in a product that is highly motivated to purchase at the present time, and performs an action such as bidding or registration of a bid candidate. For this reason, the generation unit 133 calculates the index value so that the index value becomes higher as the latest action information is generated, and generates the user feature information based on the index value. Thereby, the production | generation part 133 can produce | generate the suitable user characteristic information based on the action information assumed that a user's interest is strong.

  In addition, the production | generation part 133 produces | generates a user's feature information by extracting a keyword from a user's action information as mentioned above. Specifically, the generation unit 133 generates user feature information based on keywords extracted by performing morphological analysis on names and categories set for the products registered as candidates for purchase by the user. For example, the generation unit 133 generates feature information using a keyword extracted from a product or the like that is a commercial item on the auction site as an element of the feature information. For example, the generation unit 133 generates feature information as a word vector having a keyword (word) as an element. In this case, as described above, the generation unit 133 may generate a word vector whose elements are keywords weighted by the index values set for the keywords extracted from the behavior information including information related to the purchase stage. it can. Thereby, the production | generation part 133 can produce | generate a user's feature information as an element with a heavy weight, so that a keyword with a high user's interest is high.

  Note that the generation unit 133 selects the user's keyword based on a keyword excluding a predetermined specific word from among keywords extracted from information set for a product registered as a purchase target candidate by the user. Generate feature information. In other words, the generation unit 133 can generate feature information by excluding unnecessary words in the feature information generation process in advance. For example, when the generation unit 133 performs a morphological analysis on information on a product or service that is a commercial item on the auction site, the generation unit 133 is a keyword specific to the auction site such as “free” or “prompt decision” and indicates a user's characteristics. In some cases, keywords that cannot be assumed are extracted. In this case, for example, the generation unit 133 is a specific word that is determined in advance by the administrator of the advertising device 100 and the like, and the user's feature is determined by a keyword excluding the specific word such as “free” or “prompt decision”. Information may be generated. Thereby, since the generation unit 133 can exclude keywords that are not supposed to show the user's characteristics from the feature information, the generating unit 133 can generate the feature information that more appropriately shows the user's characteristics.

(About the request receiving unit 134)
The request reception unit 134 receives a distribution request for advertisement content. Specifically, the request reception unit 134 is a request transmitted from the user terminal 10 that displays a web page, and receives a request regarding distribution of advertisement content displayed in an advertisement frame included in the web page.

(About the extraction unit 135)
The extraction unit 135 extracts predetermined content such as advertisement content distributed to the user based on the user's behavior history acquired by the acquisition unit 132. For example, the extraction unit 135 extracts advertisement content to be distributed to the user terminal 10 based on the similarity between the user feature information generated by the generation unit 133 and the content information set in the advertisement content.

  The extraction unit 135 extracts the advertisement content distributed to the user using the advertisement category set for the advertisement content or the keyword extracted from the explanatory text describing the advertisement content as the content information set for the advertisement content. To do. For example, the extraction unit 135 extracts advertisement content to be distributed to the user using a keyword extracted by performing morphological analysis on information set in the advertisement content. As described above, the extraction unit 135 executes the extraction process using the content information based on the keyword related to the advertisement content. For example, the extraction unit 135 uses a word vector having a keyword related to the advertising content as the element as the content information of the advertising content, similarly to the user feature information generated by the generating unit 133. Accordingly, the extraction unit 135 can calculate the similarity between the user feature information generated by the generation unit 133 and the content information of the advertising content as the similarity between the word vectors.

  For example, the extraction unit 135 calculates the cosine similarity between the feature information of the user and the content information, and preferentially extracts the advertising content corresponding to the cosine similarity having a high calculated numerical value. When both the user feature information and the content information are expressed by a vector space model such as a word vector, the similarity between both word vectors can be expressed by the cosine similarity. In this case, the extraction unit 135 calculates the cosine similarity indicated in the range of “0” to “1” as the cosine similarity. Then, the extraction unit 135 determines that the advertisement content corresponding to the cosine similarity having a higher numerical value is appropriate as the content distributed to the user corresponding to the feature information for which the similarity is calculated. Thereby, the extraction unit 135 can extract the advertising content that is assumed to have a high advertising effect.

(About distribution unit 136)
The distribution unit 136 distributes the advertisement content extracted by the extraction unit 135 to the user terminal 10 corresponding to the user who has transmitted the advertisement content distribution request received by the request reception unit 134.

  Note that, as described above, the data of the advertisement content that is actually distributed may not be stored in the advertisement information storage unit 121 of the advertisement device 100. For example, the distribution unit 136 may distribute the advertisement content extracted by the extraction unit 135 to the user terminal 10 by transmitting an advertisement distribution control command to a predetermined advertisement distribution server provided outside.

[3-2. Configuration of auction server]
Next, the configuration of the auction server 30 according to the embodiment will be described with reference to FIG. FIG. 7 is a diagram illustrating a configuration example of the auction server 30 according to the embodiment. As shown in FIG. 7, the auction server 30 includes a communication unit 31, a product information storage unit 32, and a control unit 33. The auction server 30 may include an input unit that receives various operations from an administrator who uses the auction server 30 and a display unit that displays various types of information.

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

(About the product information storage unit 32)
The merchandise information 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. Here, FIG. 8 shows an example of the product information storage unit 32 according to the embodiment. In the example illustrated in FIG. 8, the product information storage unit 32 stores “product ID”, “product name”, “product category”, “bidder ID”, “current price”, “prompt decision price”, “end date and time”. It has items such as.

  “Product ID” indicates identification information for identifying a product in an auction. The “product name” indicates the name of the product that is exhibited in the auction. “Commodity category” indicates the category of the commodity for sale in the auction. “Bidder ID” indicates identification information for identifying a user who is a bidder who is bidding the highest bid price at the present time. Here, it is assumed that the information displayed in the bidder ID corresponds to the user ID shown in FIG. The “current price” indicates the highest bid price that is currently bid in the auction. The “prompt decision price” indicates a price at which the auction is immediately ended when a bid is made at the listed price. The “prompt decision price” may not be set depending on the exhibitor, and in this case, the prompt decision price item is blank. “End date and time” indicates the date and time when the auction ends.

  In FIG. 8, an auction in which the date and time is not stored in the “end date and time” is being held or has not been held, and the auction in which the date and time is stored in the “end date and time” is ended. In addition, when the date and time is stored in the “end date and time”, the current price corresponds to the winning bid price.

  For example, FIG. 8 illustrates an example in which the product identified by the product ID “G01” has the product name “AAA” and the product category “automobile”. In FIG. 8, the user identified by the bidder ID “U11” bids for “300000 yen” on the product identified by the product ID “G01”, and the end date “September 13, 2014, 10th It indicates that the process has ended with “hour 00 minutes”. Further, it is shown that the prompt decision price “500000 yen” is set for the product identified by the product ID “G01”. FIG. 8 illustrates an example in which the auction related to the product ID “G01” has ended and the auction related to the product IDs “G02” to “G07” is being held.

  In addition, the information memorize | stored in the merchandise information memory | storage part 32 is not restricted to the example shown in FIG. For example, the product information storage unit 32 may store a “minimum successful bid price” indicating the minimum price at which a successful bid can be made. The “prompt decision price” and the “minimum winning bid price” are set by the exhibitor, for example. In addition, information stored in the product information storage unit 32 includes information indicating a bid price difference such as the number of bids for each user and how much money is set for the current price and a new bid is made. It may be stored. In FIG. 8, the merchandise information storage unit 32 has shown an example of storing information related to products out of merchandise, but the merchandise information storage unit 32 stores information about services as an example of merchandise. May be.

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

  As illustrated in FIG. 7, the control unit 33 includes a reception unit 34 and a transmission unit 35, and realizes or executes information processing functions and operations described below. The internal configuration of the control unit 33 is not limited to the configuration illustrated in FIG. 7, and may be another configuration as long as the information processing described later is performed. In addition, the connection relationship between the processing units included in the control unit 33 is not limited to the connection relationship illustrated in FIG. 7, and may be another connection relationship.

(About the reception unit 34)
The accepting unit 34 accepts listing of products on the auction site, bidding on the exhibited products, and the like. The accepting unit 34 stores product information in the product information storage unit 32 when accepting an item for sale.

(About the transmitter 35)
The transmission unit 35 transmits user behavior information on the auction site. For example, the transmission unit 35 transmits behavior information related to a bid or a successful bid for the product received by the reception unit 34 to the advertising device 100. In this case, the transmission unit 35 also refers to the product information storage unit 32 and appropriately transmits information related to the product to be purchased included in the user behavior information.

[4. (Extraction procedure)
Next, the procedure of extraction processing by the extraction processing system 1 according to the embodiment will be described with reference to FIG. FIG. 9 is a sequence diagram illustrating an example of an extraction processing procedure by the extraction processing system 1 according to the embodiment.

  As shown in FIG. 9, the advertiser terminal 20 submits the advertising content to the advertising device 100 (step S101). The advertising device 100 stores the submitted advertising content in a predetermined storage unit.

  Then, the user terminal 10 accesses the auction site provided by the auction server 30 (step S102). The auction server 30 transmits the behavior information of the user terminal 10 at the auction site to the advertising device 100 (step S103).

  Advertising device 100 accumulates action information acquired from auction server 30 (Step S104). Then, the advertising device 100 generates user feature information based on the accumulated behavior information (step S105).

  Thereafter, the user terminal 10 accesses a website such as a portal site provided by the web server 40 (step S106). The web server 40 responds to the access of the user terminal 10 and transmits a web page constituting a portal site or the like to the user terminal 10 (step S107). The user terminal 10 requests advertisement distribution to the advertising device 100 in order to acquire the advertising content to be displayed in the advertising space included in the web page (step S108).

  Then, the advertising device 100 specifies the feature information of the user terminal 10 that has transmitted the advertisement distribution request according to the identification information of the user terminal 10 included in the advertisement distribution request transmitted from the user terminal 10. Then, the advertising device 100 extracts advertising content based on the similarity between the identified feature information and the content information of the advertising content that is held (step S109).

  Then, the advertising device 100 distributes the extracted advertising content to the user terminal 10 (step S110). The user terminal 10 displays the distributed advertising content on the advertising space in the web page (step S111).

  Next, procedures of generation processing and extraction processing by the advertising device 100 according to the embodiment will be described with reference to FIGS. 10 and 11. In the following, the generation processing procedure by the advertising device 100 will be described with reference to FIG. 10, and the extraction processing procedure by the advertising device 100 will be described with reference to FIG.

  First, the generation processing procedure by the advertising device 100 according to the embodiment will be described with reference to FIG. FIG. 10 is a flowchart illustrating a generation processing procedure performed by the advertising device 100 according to the embodiment.

  As illustrated in FIG. 10, the acquisition unit 132 determines whether user action information has been acquired from the auction server 30 (step S <b> 201). And the acquisition part 132 waits until it acquires, when a user's action information is not acquired (step S201; No).

  On the other hand, when the user behavior information is acquired (step S201; Yes), the acquisition unit 132 accumulates the acquired behavior information in the behavior information storage unit 122 (step S202). And the production | generation part 133 produces | generates a user's characteristic information based on the accumulate | stored action information (step S203). Then, the generation unit 133 stores the generated feature information in the feature information storage unit 123 in association with the user identification information (step S204). Thus, the generation process by the advertising device 100 is completed.

  Next, the extraction processing procedure by the advertising device 100 according to the embodiment will be described with reference to FIG. FIG. 11 is a flowchart illustrating an extraction processing procedure by the advertising device 100 according to the embodiment.

  As illustrated in FIG. 11, the request reception unit 134 determines whether an advertisement distribution request has been received from the user terminal 10 (step S <b> 301). And the request reception part 134 waits until it receives, when the request | requirement of advertisement delivery is not received (step S301; No).

  On the other hand, when the advertisement distribution is received (step S <b> 301; Yes), the request reception unit 134 passes a request for advertisement distribution to the extraction unit 135. The request reception unit 134 passes the user identification information to the extraction unit 135 together with the advertisement distribution request.

  Based on the user identification information, the extraction unit 135 determines whether or not the feature information storage unit 123 holds feature information corresponding to the user (step S302). Then, when the feature information corresponding to the user terminal that transmitted the advertisement distribution request is not held (step S302; No), the extraction unit 135 skips step S303 described below.

  On the other hand, when the feature information corresponding to the user terminal that transmitted the advertisement distribution request is retained (step S302; Yes), the extraction unit 135 corresponds to the content information of the retained advertisement content and the user. The similarity with the feature information is calculated (step S303).

  Then, when the similarity is calculated, the extraction unit 135 extracts advertisement content corresponding to the user based on the calculated similarity (step S304). Note that, when the similarity is not calculated, the extraction unit 135 extracts advertisement content corresponding to the user who transmitted the advertisement distribution request according to a general advertisement allocation procedure. Then, the distribution unit 136 distributes the advertising content extracted by the extraction unit 135 to the user terminal 10 (step S305). Thus, the extraction process by the advertising device 100 is completed.

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

[5-1. Learning)
In the extraction process according to the embodiment described above, the acquisition unit 132 has shown an example of acquiring user information when the user terminal 10 accesses a website provided by the auction server 30. However, the acquisition unit 132 is not limited to the case where the user terminal 10 accesses a website provided by the auction server 30, and may acquire user information corresponding to the user terminal 10.

  For example, the acquisition unit 132 acquires behavior information transmitted from the user terminal 10 after the advertising content extracted by the extraction unit 135 is distributed to the user terminal 10. For example, the acquisition unit 132 has performed CTR, which is an index indicating the rate at which the user terminal 10 has clicked on the distributed advertising content, or an action that brings some benefit to the advertiser by the distributed advertising content (that is, , Conversions, etc.). And the acquisition part 132 acquires the information regarding the keyword used as the opportunity which extracts this advertising content regarding the advertising content measured relatively highly in advertising effectiveness. Then, the acquisition unit 132 passes the acquired information to the generation unit 133.

  Then, the generation unit 133 updates the feature information corresponding to the user terminal 10 based on the information related to the keyword acquired by the acquisition unit 132 regarding the feature information stored in the feature information storage unit 123. That is, the generation unit 133 recalculates the index value for the keyword that triggered the extraction of the advertising content for which the high advertising effectiveness was measured, and weighted by the index value. Update to feature information.

  Then, when there is a new advertisement distribution request from the user terminal 10, the extraction unit 135 extracts advertisement content based on the updated feature information.

  As described above, the advertising device 100 acquires the index value indicating the advertising effect of the distributed advertising content, and updates the feature information based on the acquired index value indicating the advertising effect even after the advertising content is extracted. can do. In other words, the advertising device 100 can extract more appropriate advertising content (that is, advertising content with high advertising effect) by repeating machine learning that reflects the results regarding the generation processing and extraction processing described above. Can be generated. Thereby, the advertising device 100 can further improve the accuracy of extracting appropriate advertising content corresponding to the user.

[5-2. (Indicator value)
In the generation process according to the above-described embodiment, the generation unit 133 has shown an example in which the index value for each keyword is calculated based on the information related to the stage leading to the user purchase at the auction site. However, without being limited to the above example, the generation unit 133 may calculate an index value indicating the weighting of the keyword using further different information.

  For example, the generation unit 133 may calculate the index value of the corresponding keyword based on the number of bids of the user terminal 10 regarding the specific product of the user terminal 10 on the auction site. Since auctions are repeated at the auction site, it is assumed that the same user repeats bidding for the same product multiple times. The acquisition unit 132 appropriately acquires information on the number of bid actions of the user as described above on the auction site. Then, the generation unit 133 calculates an index value for each keyword based on the information acquired by the acquisition unit 132. Thereby, the production | generation part 133 can produce | generate the feature information which shows the user's feature more weighted about the keyword corresponding to the goods assumed that purchase willingness is higher. For this reason, the extraction unit 135 can extract advertisement content more suitable for the user.

  The acquisition unit 132 may acquire further different information regarding the auction. For example, the acquisition unit 132 acquires information about a bid price set by the user when bidding. In an auction, it is assumed that a user who bids for an auction by presenting a relatively high amount with respect to the current price of a specific product has a higher willingness to purchase such a product than other users. In this case, the generation unit 133 uses information regarding the difference between the current price and the bid price as an element for calculating the weight. Thereby, the production | generation part 133 can produce | generate the feature information according to a user's willingness to purchase more. Further, the generation unit 133 calculates an index value indicating weighting based on information such as whether or not the user is bidding on similar products at the same time and whether or not similar products are registered in the watch list. May be. For example, the generation unit 133 sets a high index value so that weighting is increased for keywords extracted from a similar group of products for which many bids are made.

[5-3. (Data acquisition)
In the extraction process according to the above-described embodiment, the acquisition unit 132 has shown an example of acquiring user information when the user terminal 10 accesses a website provided by the auction server 30 and the web server 40. However, the acquisition unit 132 is not limited to the case where the user terminal 10 accesses the website provided by the auction server 30 and the web server 40, and may acquire user information from the user terminal 10. This point will be described below.

  As described above, the acquisition unit 132 according to the embodiment uses the notification function such as a web beacon embedded in a website provided by the auction server 30 and the web server 40 to obtain user information from the user terminal 10. You may get it.

  Further, the acquisition unit 132 is provided from a predetermined web server managed by the same management device as the management device that manages the advertising device 100 (for example, a front-end server for the advertising device 100) that is accessed by the user terminal 10 If it is, the acquisition unit 132 can acquire user information from the user terminal 10. That is, when the user terminal 10 accesses a website provided by a predetermined web server managed by the management apparatus, the user terminal 10 transmits user information of the user terminal 10 to the management apparatus. This is realized by the user terminal 10 transmitting a cookie to the management apparatus. In this case, the user information transmitted from the user terminal 10 is transmitted to the acquisition unit 132 included in the advertising device 100 via the management device. Thereby, the acquisition unit 132 can acquire the user information of the user terminal 10 without going through the auction server 30 and the web server 40. The acquisition unit 132 relates to the acquired user information by checking the cookie transmitted from the user terminal 10 or the device ID set in advance in the user terminal 10. Each user terminal 10 can be identified.

  In addition, the acquired user information is not restricted to the aspect utilized for advertisement delivery, You may utilize for other various uses. For example, the user information acquired by the advertising device 100 is used for content distribution (for example, mail distribution to extracted users) based on a user list or the like held by the advertising device 100. May be.

[5-4. (Conditions accepted from advertisers)
In the embodiment described above, the submission accepting unit 131 has shown an example in which the advertisement content is received from the advertiser together with the advertisement category and the advertisement keyword. However, the submission accepting unit 131 may accept submission of advertising content together with further different information.

  For example, the submission accepting unit 131 may accept the number of advertisement contents desired to be distributed, the amount of advertisement content distributed per time, and the designation of CPA (Cost Per Acquisition) from the advertiser. The CPA indicates the cost per number of new customers acquired when conversion is performed by the advertising content (new customers are acquired). CPA is obtained by dividing the advertising cost by the number of conversions, and the lower the CPA value, the better the advertising efficiency.

  In this case, the extraction unit 135 may extract the advertising content while determining various conditions received from the advertiser. For example, the extraction unit 135 appropriately extracts the advertising content to be extracted by appropriately changing the threshold setting regarding the degree of similarity between the target user predicted to be converted and the content information of the advertising content according to a predetermined condition. You may adjust.

[5-5. Aspects of commercial transaction service]
In embodiment mentioned above, the acquisition part 132 showed the example which acquires the action information when the user terminal 10 accesses the website (for example, auction site) which provides commercial transaction. Here, the information acquired by the acquisition unit 132 is not limited to the behavior information of the website that provides the commercial transaction service. For example, a commercial transaction service such as an auction site via a communication network may be provided mainly by an application (App) developed for a smart device. The acquisition unit 132 may acquire user behavior information in a service provided by the application via a network, as in the above-described embodiment. Then, the extraction unit 135 can extract predetermined content distributed to the user based on the user's behavior history acquired by the acquisition unit 133. In other words, the “commerce service provided via a communication network” in the above-described embodiment refers to not only a service site provided via a web browser, but also a service provided within an application, and other communication networks. It is a concept that includes all the commercial transaction services provided through the Internet.

[5-6. (Feature information)
In the embodiment described above, the generation unit 133 sets a predetermined index value for each keyword extracted from the user's behavior history, generates user feature information weighted by the set index value, and generates the generated feature. An example in which information is stored in the feature information storage unit 123 is shown. Here, the generation unit 133 stores the feature information stored in the feature information storage unit 123, not the weighted feature information, but information for calculating the user behavior information and the weight of the behavior information (for example, the action date and time, etc. ). In this case, the generation unit 133 generates the weighted user feature information as described above at a timing when the request reception unit 134 requests the advertisement distribution. Thereby, the production | generation part 133 can generate | occur | produce the weighted characteristic information by determining how long it was the action information performed from the time of the advertisement delivery request | requirement from a user.

[6. Hardware configuration)
Further, the advertising device 100 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in FIG. 12, for example. Hereinafter, the advertisement apparatus 100 will be described as an example. FIG. 12 is a hardware configuration diagram illustrating an example of a computer 1000 that implements the functions of the advertising device 100. The computer 1000 includes a CPU 1100, RAM 1200, ROM 1300, HDD 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700.

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

  The HDD 1400 stores a program executed by the CPU 1100, data used by the program, and the like. The communication interface 1500 receives data from other devices via the communication network 500 (corresponding to the network N shown in FIG. 2), sends the data to the CPU 1100, and transmits the data generated by the CPU 1100 to the other devices via the communication network 500. Send to.

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

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

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

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

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured. For example, the acquisition unit 132 and the generation unit 133 illustrated in FIG. 3 may be integrated. Further, for example, information stored in the storage unit 120 may be stored in a storage device provided outside via the network N.

  Further, for example, in the above-described embodiment, an example is shown in which the advertising device 100 performs a generation process for generating user feature information, an extraction process for extracting distributed advertising content, and a distribution process for distributing advertising content. It was. However, the advertising device 100 described above may be separated into a generation device that performs generation processing, an extraction device that performs extraction processing, and a distribution device that performs distribution processing. In this case, the generation apparatus includes an acquisition unit 132 and a generation unit 133. In addition, the extraction apparatus includes a submission receiving unit 131 and an extraction unit 135. In addition, the distribution apparatus includes a submission reception unit 131, a request reception unit 134, and a distribution unit 136.

  Moreover, each embodiment mentioned above can be combined suitably in the range which does not contradict a process content.

[8. effect〕
As described above, the advertising device 100 according to the embodiment includes, among information related to a user, a website (an example of a commercial transaction service provided via a communication network) that provides a commercial transaction service such as an auction site. An acquisition unit 132 that acquires an action history in which a specific product is registered as a candidate for purchase, and an advertisement content (an example of content) distributed to the user based on the user's action history acquired by the acquisition unit 132 And an extraction unit 135 for extracting.

  As described above, the advertising device 100 according to the embodiment includes a bid on a commercial transaction site such as an auction site in addition to user attribute information, user website browsing information, and the like that are used in general targeting advertisements. The advertising content is extracted using information extracted from the action history. Thereby, the advertising device 100 can improve the accuracy of extracting content with a high appealing effect to the user.

  In addition, the advertising device 100 according to the embodiment further includes a generation unit 133 that generates feature information indicating a feature of the user based on a keyword extracted from the user's behavior history acquired by the acquisition unit 132. Then, the extraction unit 135 extracts the advertisement content distributed to the user based on the similarity between the user feature information generated by the generation unit 133 and the content information set in the advertisement content.

  As described above, the advertising device 100 according to the embodiment generates user feature information using information extracted from an action history such as bidding on a commercial transaction site such as an auction site. The advertising device 100 calculates the similarity between the generated user feature information and the content information, and extracts the advertising content based on the calculated similarity. The accuracy of extraction can be improved.

  The generation unit 133 sets a predetermined index value for each keyword extracted from the user's behavior history, and generates user feature information weighted by the set index value.

  As described above, the advertising device 100 according to the embodiment uses the weighted keyword corresponding to the actual action of the user, and thus can generate feature information that appropriately indicates the feature of the user.

  Further, the generation unit 133 sets a predetermined index value so that the keyword extracted from the latest information in the user's behavior history has a higher numerical value, and the user characteristic information weighted by the set index value is set. Generate.

  As described above, the advertising device 100 according to the embodiment uses the weighted keyword corresponding to the actual action of the user to which the time information is added. That is, the advertising device 100 can generate feature information using keywords that are weighted based on information that the user is assumed to have a strong desire to purchase.

  In addition, the generation unit 133 generates user feature information based on keywords extracted from information set in a product registered as a purchase target candidate by the user.

  As described above, the advertising device 100 according to the embodiment extracts a keyword based on information set in the product in addition to the product itself that the user is willing to purchase. For this reason, since the advertising device 100 can extract a large number of elements that generate user characteristic information, the advertising content can be extracted using more information than behavior information such as general web browsing history. Can be executed.

  In addition, the generation unit 133 selects the user's keyword based on a keyword excluding a predetermined specific word from the keywords extracted from information set in the product registered as a purchase target candidate by the user. Generate feature information.

  As described above, the advertising device 100 according to the embodiment can exclude keywords that are not supposed to indicate the user's features from the feature information even if the keywords are extracted from the merchandise. The feature information shown can be generated.

  Further, the generation unit 133 generates user feature information using information included in the user's behavior history and indicating the stage until the user makes a purchase.

  Thereby, the advertising device 100 according to the embodiment can express the characteristics of the user in accordance with the actual behavior of the user. For this reason, the advertising device 100 can generate feature information according to the user's willingness to purchase.

  Further, the extracting unit 135 uses the keyword extracted from the category set for the advertising content or the explanatory text explaining the advertising content among the content information set for the advertising content, to the advertising content distributed to the user To extract.

  Thereby, the advertising device 100 according to the embodiment can appropriately calculate the similarity between the feature information generated by the keyword extracted from the user behavior information and the advertising content. As an example, the advertising device 100 can calculate the cosine similarity between the feature information of the user and the content information based on the keyword. For this reason, since the advertising device 100 can extract the advertising content based on the objective similarity between the feature information and the content information, it can improve the accuracy of extracting the advertising content having a high advertising effect for the user. .

  In addition, the acquisition unit 132 acquires at least one of information indicating a bid for a product, a successful bid for the product, and registration as a bid candidate for the product as a user's action history. The extraction unit 135 uses at least one of information indicating the bid for the product on the auction site, the successful bid for the product, and the registration to the bid candidate of the product among the information acquired by the acquisition unit 132, The advertising content distributed to the user is extracted.

  As described above, when the user uses an auction site, the advertising device 100 according to the embodiment extracts advertising content using information indicating a stage leading to purchase such as a bid or a successful bid. Thereby, the advertising device 100 can extract the advertising content based on the information indicating the user's high willingness to purchase.

  In addition, the acquisition unit 132 acquires at least one of information indicating a bid for a product, a successful bid for the product, and registration as a bid candidate for the product as a user's action history. Of the information acquired by the acquisition unit 132, the generation unit 133 includes a keyword extracted from an action history corresponding to a bid for a product on an auction site or registration of a product as a bid candidate. An index value that is higher than that of the keyword extracted from the action history corresponding to the successful bid is set, and user feature information is generated using the keyword weighted by the set index value.

  In other words, the advertising device 100 according to the embodiment sets a higher weight for keywords extracted from bids for merchandise and registration in the watch list than keywords extracted from successful bids. Thereby, the advertising device 100 can generate feature information that more reflects the user's intention by using the information related to the purchase stage of the user.

  In addition, the advertising device 100 according to the embodiment includes a request reception unit 134 that receives a distribution request for advertisement content from the user terminal 10 corresponding to the user, and a user terminal that has transmitted the distribution request for advertisement content received by the request reception unit 134 10 further includes a distribution unit 136 that distributes the advertising content extracted by the extraction unit 135.

  Thereby, since the advertising device 100 according to the embodiment can distribute the advertising content extracted along the interest of the user to the user, the advertising effect of the advertising content can be improved.

  As described above, some of the embodiments of the present application have been described in detail with reference to the drawings. However, these are merely examples, and various modifications, including the aspects described in the disclosure section of the invention, based on the knowledge of those skilled in the art, It is possible to implement the present invention in other forms with improvements.

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

DESCRIPTION OF SYMBOLS 1 Extraction processing system 10 User terminal 20 Advertiser terminal 30 Auction server 40 Web server 100 Advertising apparatus 110 Communication part 120 Storage part 121 Advertisement information storage part 122 Behavior information storage part 123 Feature information storage part 130 Control part 131 Submission acceptance part 132 Acquisition unit 133 Generation unit 134 Request reception unit 135 Extraction unit 136 Distribution unit

Claims (17)

Among the information about the user, in a commercial transaction service provided via a communication network, an acquisition unit that acquires an action history indicating a result of whether or not a specific product has been purchased from the user;
An extraction unit that extracts predetermined content distributed to the user based on the user's behavior history acquired by the acquisition unit;
An extraction device comprising: Among the information about the user, an acquisition unit that acquires information indicating a stage until the user purchases a product as a user's behavior history in a commercial transaction service provided via a communication network;
An extraction unit that extracts predetermined content distributed to the user based on information acquired by the acquisition unit and indicating a stage until the user purchases a product;
An extraction device comprising: The acquisition unit
In the commerce service, the user further acquires an action history in which a specific product is registered as a candidate for purchase by the user,
The extraction unit includes:
Extracting predetermined content distributed to the user based on an action history in which a specific product is registered as a candidate for purchase by the user;
The extraction apparatus according to claim 1 or 2, wherein Based on a keyword extracted from the user's behavior history acquired by the acquisition unit, a generation unit that generates feature information indicating the characteristics of the user,
Further comprising
The extraction unit includes:
Extracting content to be distributed to the user based on the similarity between the feature information of the user generated by the generation unit and content information set to the content;
The extraction device according to claim 3. The generator is
A predetermined index value is set for each keyword extracted from the user's behavior history, and the feature information of the user weighted by the set index value is generated.
The extraction apparatus according to claim 4. The generator is
In the user's behavior history, the index value is set so that the numerical value becomes higher as the keyword extracted from the latest information, and the feature information of the user weighted by the set index value is generated.
The extraction device according to claim 5. The generator is
Generating feature information of the user based on keywords extracted from information set in the product registered as a candidate for purchase by the user;
The extraction device according to any one of claims 4 to 6, wherein The generator is
Generating feature information of the user based on a keyword excluding a predetermined specific word among keywords extracted from information set in the product registered as a purchase target candidate by the user To
The extraction apparatus according to claim 7. The generator is
Using the information included in the user's behavior history and indicating the stage until the user purchases, to generate the feature information of the user,
The extraction device according to any one of claims 4 to 8, wherein The extraction unit includes:
Extracting content to be distributed to the user using a keyword extracted from a category set in the content or an explanatory text explaining the content from content information set in the content,
The extraction device according to any one of claims 4 to 9, wherein The acquisition unit
As the user's action history, obtain at least one of information indicating a bid for a product at a predetermined auction site, a successful bid for the product, and registration to a bid candidate for the product,
The extraction unit includes:
The information acquired by the acquisition unit is distributed to the user using at least one of information indicating a bid for a product at the auction site, a successful bid for the product, and registration as a bid candidate for the product. Content to be extracted,
The extraction device according to any one of claims 1 to 10, wherein The acquisition unit
As the user's action history, obtain at least one of information indicating a bid for a product at a predetermined auction site, a successful bid for the product, and registration to a bid candidate for the product,
The generator is
Of the information acquired by the acquisition unit, a keyword extracted from an action history corresponding to a bid for a product on the auction site or registration of a product as a bid candidate corresponds to a successful bid for the product. Set the index value that is higher than the keyword extracted from the action history, and generate the feature information of the user using the keyword weighted by the set index value.
The extraction apparatus according to claim 5 or 6, characterized in that: A receiving unit that receives a distribution request for the predetermined content from a terminal device corresponding to the user;
A distribution unit that distributes the predetermined content extracted by the extraction unit to the terminal device that has transmitted the distribution request for the predetermined content received by the reception unit;
The extraction device according to claim 1, further comprising: An extraction method performed by a computer,
Among the information about the user, in the commercial transaction service provided via the communication network, an acquisition step of acquiring an action history indicating a result of whether or not a specific product is purchased from the user;
An extraction step of extracting predetermined content distributed to the user based on the user's behavior history acquired by the acquisition step;
The extraction method characterized by including. Among the information about the user, in a commercial transaction service provided via a communication network, an acquisition procedure for acquiring an action history indicating a result of whether or not a specific product has been purchased from the user;
An extraction procedure for extracting predetermined content distributed to the user based on the user's behavior history acquired by the acquisition procedure;
An extraction program characterized by causing a computer to execute. An extraction method performed by a computer,
Among the information about the user, as a user's behavior history in a commercial transaction service provided via a communication network, an acquisition step of acquiring information indicating a stage until the user purchases a product;
An extraction step of extracting predetermined content distributed to the user based on information obtained by the acquisition step and indicating a stage until the user purchases a product;
The extraction method characterized by including. Among the information about the user, as a user's behavior history in a commercial transaction service provided via a communication network, an acquisition procedure for acquiring information indicating a stage until the user purchases a product;
An extraction procedure for extracting predetermined content to be distributed to the user based on information acquired by the acquisition procedure and indicating a stage until the user purchases a product;
An extraction program characterized by causing a computer to execute.

Images