JP6791785B2 - Advertising device, advertisement extraction method, advertisement extraction program, terminal device and terminal control program - Google Patents

Description

The present invention relates to an advertisement device, an advertisement extraction method, an advertisement extraction program, a terminal device, and a terminal control program.

In recent years, with the rapid spread of the Internet, advertisement distribution via the Internet has been actively carried out. For example, advertising content such as a company or a product is displayed in an advertising space set on a web page, and when the advertising content is clicked, an advertisement is delivered that transitions to the advertiser's web page.

In such advertisement distribution, a technique for distributing an advertisement of interest to a user has been proposed in order to enhance the advertisement effect. For example, a keyword is specified from the content that presents the article posted by the user and the article posted by another user associated with the user in chronological order, and an advertisement related to the specified keyword is delivered as an advertisement to be displayed together with the content. (Patent Document 1).

Japanese Unexamined Patent Publication No. 2014-75006

However, the above-mentioned conventional technique does not always improve the advertising effect. Specifically, the above-mentioned conventional technology is merely a technology for delivering an advertisement of interest to a user based on a posted article for each user who uses a Web posting service such as Twitter (registered trademark), and the existence of the posted article. It is not always possible to enhance the advertising effect in the advertisement distribution that does not, that is, the advertisement distribution that is widely performed.

The present application has been made in view of the above, and an object of the present application is to provide an advertising device, an advertising extraction method, an advertising extraction program, a terminal device, and a terminal control program capable of enhancing the advertising effect.

The advertising device according to the present application is the degree of relevance between the advertisement content of the distribution candidate displayed in a list together with the content and the content displayed around the arrangement position where the advertisement content of the distribution candidate is arranged. Calculated by a calculation unit that calculates an index value indicating the degree of relevance that fluctuates with a weight value based on the distance between the advertisement content and the content displayed around the placement position where the advertisement content of the distribution candidate is placed, and the calculation unit. It is characterized by having an extraction unit that extracts the advertisement content to be distributed from the advertisement content of the distribution candidate based on the index value.

According to one aspect of the embodiment, there is an effect that the advertising effect can be enhanced.

FIG. 1 is a diagram showing an example of an advertisement extraction process according to the first embodiment. FIG. 2 is a diagram showing a configuration example of the advertisement extraction system according to the first embodiment. FIG. 3 is a diagram showing a configuration example of the advertising device according to the first embodiment. FIG. 4 is a diagram showing an example of the advertisement information storage unit according to the first embodiment. FIG. 5 is a diagram showing an example of the index value calculation process according to the first embodiment. FIG. 6 is an explanatory diagram for specifically explaining the advertisement extraction process according to the first embodiment. FIG. 7 is a flowchart showing an advertisement extraction processing procedure by the advertisement device according to the first embodiment. FIG. 8 is a diagram showing an example of categorization according to the modified example in the first embodiment. FIG. 9 is a diagram showing a configuration example of the advertising device according to the second embodiment. FIG. 10 is a diagram showing an example of an advertisement extraction process by the advertisement extraction system according to the second embodiment. FIG. 11 is a diagram showing a configuration example of the advertisement extraction system according to the third embodiment. FIG. 12 is a diagram showing a configuration example of the user device according to the third embodiment. FIG. 13 is a diagram showing an example of an advertisement extraction process according to another embodiment. FIG. 14 is a hardware configuration diagram showing an example of a computer that realizes the function of the advertising device.

Hereinafter, modes for implementing the advertisement device, advertisement extraction method, advertisement extraction program, terminal device, and terminal control program according to the present application (hereinafter, referred to as “embodiments”) will be described with reference to the drawings. It should be noted that this embodiment does not limit the advertising device, the advertisement extraction method, and the advertisement extraction program according to the present application. Further, in the following embodiments, the same parts are designated by the same reference numerals, and duplicate description is omitted.

(First Embodiment)
[1. Advertisement extraction process]
Hereinafter, an example of the advertisement extraction process according to the first embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of an advertisement extraction process according to the first embodiment. FIG. 1 shows an example in which the advertisement extraction process is performed by the advertisement device 100.

The advertising device 100 accepts submission of advertising content from an advertiser. Then, when the advertising device 100 receives an advertisement request that is a request for acquiring the advertisement content included in the web page W1 from the user terminal 10, the advertisement content received from the advertiser, that is, the advertisement to be distributed from the advertisement content of the distribution candidate. Extract content. Specifically, the advertising device 100 calculates an index value indicating the degree of relevance between the advertisement content of the distribution candidate and the content displayed around the arrangement position where the advertisement content is arranged on the web page W1. Then, the advertising device 100 extracts the advertisement content to be distributed from the advertisement content of the distribution candidate based on the calculated index value.

First, the web page W1 according to the first embodiment will be described. As shown in FIG. 1A, the web page W1 according to the embodiment is a plurality of contents arranged in the vertical direction. Further, as a result, a plurality of contents are displayed in a list on the display screen of the user terminal 10.

In this way, the plurality of contents displayed in the list are roughly classified into article contents and advertisement contents. Article content is, for example, news articles, entertainment information, blogs, etc., and indicates content other than advertising content. Advertising content is placed between article content. And, the advertisement content of such a posting method is sometimes called "in-feed advertisement" or the like.

Further, in FIG. 1A, seven contents including advertisement contents are arranged in a vertical row as a web page W1, but in the present embodiment, the web page W1 has 21 contents. Are arranged in a vertical row. In such a case, in response to one request from the user terminal 10, 21 contents including the advertisement content are not delivered to the user terminal 10 at once as the web page W1, but a predetermined number (for example, 7). ) By distribution, a web page W1 containing 21 contents is finally formed.

For example, after the web page W1a in which seven contents are arranged in a vertical row is initially displayed, the web page W1a is moved upward by a user operation, and the seventh content from the top (FIG. 1 (a)). In the example, when the article content F) is included in the display screen, the user terminal 10 transmits the request again to acquire the web page W1b in which the seven contents are arranged in a vertical row. Then, the user terminal 10 displays a web page W1 in which the web page W1b is connected under the web page W1a.

By the way, the web page W1 according to the first embodiment has been described so far. Hereinafter, the advertisement extraction process by the advertisement device 100 will be specifically described.

For example, it is assumed that a request for a web page W1a, which is an initially displayed portion of a web page W1 containing 21 contents, is transmitted from the user terminal 10. In response to this, as shown in FIG. 1B, the content server 30 determines the article contents C2 to C6 as the article contents to be distributed, and decides to arrange the article contents C2 to C6 in order from the top. And.

Further, the content server 30 transmits to the advertising device 100 a list 1 in which the text including the title, description, etc. of each determined article content is associated with the order. For example, in the list 1, the content server 30 associates the text information of the explanatory text such as "Drama X Episode 10 audience rating is 11.5%" with the order "1" for the article content C1.

Here, when seven contents are arranged in a vertical row, it is assumed that it is predetermined to insert the advertisement content at the arrangement position L1 which is an intermediate position. When the advertising device 100 receives the list 1 from the content server 30, it calculates an index value indicating the degree of relevance between the advertising content of the distribution candidate and the article content displayed around the arrangement position L1. The index value indicating the degree of relevance is a numerical value of the degree of relevance between the advertisement content and the article content, and it can be said that the higher the index value indicating the degree of relevance, the higher the relevance between the two. In the following embodiments, the index value indicating the degree of relevance may be simply referred to as “index value”.

Further, in the present embodiment, the "article content displayed around the placement position of the advertisement content" means the article content up to two above and below the placement position of the advertisement content. In the example of FIG. 1B, the article contents displayed around the arrangement position L1 indicate the article contents C2 to C5. The "article content displayed around the placement position of the advertisement content" is not limited to such an example, and indicates, for example, article content up to three above and below the placement position of the advertisement content. May be good. In addition, it may indicate the article content up to the upper four articles and the article content up to the lower two articles from the placement position of the advertisement content.

As shown in FIG. 1B, it is assumed that the advertising device 100 has the advertising contents AD1 to AD3 as the advertising contents of the distribution candidates. Therefore, when the advertising device 100 receives the list 1, the advertising device 100 calculates the similarity between the advertising content of each distribution candidate and each of the article contents C2 to C5, and calculates the sum of the calculated similarity as an index value.

In FIG. 1B, the advertising device 100 calculates four similarities between the advertising content AD1 and the article contents C2 to C5, and calculates the sum of the calculated four similarity as the index value “S1”. An example is shown. Further, in the same manner, the advertising device 100 calculates four similarities between the advertising content AD2 and the article contents C2 to C5, and calculates the sum of the calculated four similarities as the index value “S2”. Is shown. Further, an example in which the advertising device 100 calculates the index value “S3” for the advertising content AD3 is shown.

Here, the advertising content AD3 is advertising content having content related to sports. Further, of the four article contents C2 to C5, two of the article contents C3 and C4 are article contents having contents related to sports. Therefore, the advertising device 100 calculates the index value "S3" of the advertising content AD3 and the article contents C2 to C5 to be the highest. Then, the advertising device 100 extracts the advertising content AD3 for which the highest index value "S3" is calculated from the advertising content of the distribution candidate as the advertising content to be distributed.

Further, as a result, the web page W1a arranged from the top in the order of the article contents C1, C2, C3 and the advertisement contents AD3, C4, C5, C6 is delivered to the user terminal 10.

Whether or not the user is interested in the in-feed advertisement shown in FIG. 1 and clicks on it may be influenced by the article content around the advertisement content. For example, if the advertisement content related to sports is inserted while the article content related to sports is collected, the user's interest in sports is obtained by including the article content related to sports before the advertisement content related to sports is included in the user's view. Will increase. This tends to make it easier for users to click on advertising content related to such sports.

On the other hand, for example, when the advertisement content related to fashion is inserted while the article content related to sports is collected, it is unlikely that the user who has increased interest in sports clicks the advertisement content related to fashion.

That is, the advertising device 100 according to the first embodiment considers the above-mentioned characteristics of the user and calculates an index value indicating the degree of relevance between the advertising content and the article content to the surrounding article content. Since it is possible to extract advertising content having a higher affinity and display the extracted advertising content, it is possible to enhance the advertising effect.

[2. System configuration]
The configuration of the advertisement extraction system 1 according to the first embodiment will be described with reference to FIG. FIG. 2 is a diagram showing a configuration example of the advertisement extraction system 1 according to the first embodiment. As shown in FIG. 2, the advertisement extraction system 1 includes a user terminal 10, an optimization server 20, a content server 30, and an advertisement device 100. The user terminal 10, the optimization server 20, the content server 30, and the advertising device 100 are connected to each other via a network so as to be able to communicate by wire or wirelessly. The advertisement extraction system 1 shown in FIG. 2 may include a plurality of user terminals 10, a plurality of optimization servers 20, a plurality of content servers 30, and a plurality of advertisement devices 100. ..

The user terminal 10 is an information processing device used by the user. For example, the user terminal 10 is a mobile phone such as a smartphone, a tablet terminal, a PDA (Personal Digital Assistant), a desktop PC (Personal Computer), a notebook PC, or the like. For example, the user terminal 10 transmits an acquisition request (request) of the web page W1 which is list information including a plurality of contents shown in FIG. 1 to the optimization server 20 according to a user operation. Further, the user terminal 10 displays the web page W1 received from the optimization server 20 on the display screen.

The optimization server 20 is a front-end server that directly sends and receives information to and from the user terminal 10. For example, when the optimization server 20 receives the request for the web page W1 from the user terminal 10, it transmits a content request, which is an article content acquisition request, to the web server 30, and also sends an advertisement content acquisition request to the advertising device 100. Send an ad request that is. Further, the optimization server 20 generates a web page W1 using the article content received from the content server 30 and the advertisement content received from the advertising device 100, and distributes the generated web page W1 to the user terminal 10. In contrast to such an optimization server 20, the content server 30 and the advertising device 100 can be said to be back-end servers.

The content server 30 is a server device that delivers article content to the optimization server 20. For example, when the content server 30 receives a content request from the optimization server 20, the content server 30 determines the order of the article content to be distributed and the article content to be distributed. Then, the content server 30 associates the determined article content to be distributed with the order and distributes it to the optimization server 20.

The advertising device is a server device that delivers advertisements. When the advertising device 100 receives the content request from the optimization server 20, it extracts the advertisement content to be distributed from the advertisement information storage unit 120 by performing the advertisement extraction process shown in FIG. Then, the advertising device 100 delivers the extracted advertising content to the optimization server 20.

[3. Data flow]
Next, with reference to FIG. 2, the advertisement extraction process by the advertisement extraction system 1 according to the first embodiment will be described while clarifying the data flow. The description will be omitted with respect to the point where the description overlaps with that of FIG.

First, it is assumed that the user terminal 10 transmits a request for the web page W1a, which is the initially displayed portion of the web page W1, to the optimization server 20 according to the user operation, as described in FIG. 1 (step S11). ). When the optimization server 20 receives the request of the web page W1a, the optimization server 20 sends a content request for acquiring the article content included in the web page W1a to the content server 30, and also acquires the advertisement content included in the web page W1a. The advertisement request is transmitted to the advertisement device 100 (step S12).

When the content server 30 receives a content request from the optimization server 20, for example, the content server 30 refers to a predetermined storage unit in its own device that stores various article contents, and the article content to be distributed and the article content to be distributed. The order is determined (step S13). Further, the content server 30 generates a list 1 that lists the determined information. List 1 shown in FIG. 2 shows that the content server 30 has decided to arrange the article contents C1 to C6 to be distributed in a vertical row such as the first, second, and so on from the top. Further, an example is shown in which the content server 30 associates text information such as a title and a description with each article content to be distributed.

For example, in FIG. 2, the content server 30 associates the conceptual text information “T1” with the article content C1, but in reality, as described in FIG. 1 (b), “Drama X No. 10”. An explanation such as "The audience rating is 11.5%" is associated with it. The text information of the article contents C2 to C6 is also as illustrated in FIG. 1 (b). Further, as shown in Listing 1, it is assumed that it is predetermined to insert the advertisement content at the arrangement position L1 (here, the fourth from the top) which is an intermediate position.

The content server 30 transmits the list 1 generated in this way to the advertising device 100 (step S14). Further, as shown in Listing 1, the content server 30 associates the data of the article content to be distributed with the arrangement order and transmits the data to the optimization server 20 (step S15).

The advertising device 100 refers to the list 1 received from the content server 30, calculates an index value indicating the degree of relevance between the advertisement content of the distribution candidate and the article content group displayed around the placement position L1, and is the calculated index. The advertisement content to be delivered is extracted based on the value (step S16). Since the advertisement extraction process has been described with reference to FIG. 1, the description thereof will be omitted.

Then, the advertising device 100 transmits the extracted advertising content AD3 to the optimization server 20 (step S17). The optimization server 20 generates a web page W1a by using the article contents C1 to C6 received from the content server 30 and the advertisement content AD3 received from the advertising device 100 (step S18). Then, the optimization server 20 distributes the generated web page W1a to the user terminal 10 (step S19).

Here, it is assumed that the web page W1a displayed on the display screen of the user terminal 10 is moved upward by the user operation, and the seventh article content C6 is included in the display screen. In such a case, the user terminal 10 transmits a request for acquiring the web page W1b to be connected and displayed under the web page W1a to the optimization server 20 (step 21). It should be noted that it may be arbitrarily determined at what position the content is included in the display screen to send the request.

When the optimization server 20 receives the request of the web page W1b, the optimization server 20 sends a content request for acquiring the article content included in the web page W1b to the content server 30, and also acquires the advertisement content included in the web page W1b. The advertisement request for this is transmitted to the advertisement device 100 (step S22).

When the content server 30 receives a content request from the optimization server 20, for example, the content server 30 refers to a predetermined storage unit in its own device that stores various article contents, and the article content to be distributed and the article content to be distributed. The order is determined (step S23). Further, the content server 30 generates a list 2 that lists the determined information. List 2 shown in FIG. 2 shows that the content server 30 has decided to arrange the article contents C7 to C12 to be distributed in a vertical row such as the 8th, 9th ... 14th from the top. Further, an example is shown in which the content server 30 associates text information such as a title and a description with each article content to be distributed. Further, as shown in Listing 2, it is assumed that it is predetermined to insert the advertisement content at the arrangement position L2 (here, the eleventh from the top) which is an intermediate position.

The content server 30 transmits the list 2 generated in this way to the advertising device 100 (step S24). Further, as shown in Listing 2, the content server 30 associates the article content to be distributed with the order and transmits it to the optimization server 20 (step S25).

The advertising device 100 refers to the list 2 received from the content server 30, calculates an index value indicating the degree of relevance to the advertisement content of the distribution candidate and the article content group displayed around the placement position L2, and calculates the index value. Based on the above, the advertisement content to be delivered is extracted (step S26). Here, it is assumed that the advertising device 100 determines the advertising content AD1 as the advertising content to be distributed.

The advertising device 100 transmits the extracted advertising content AD1 to the optimization server 20 (step S27). The optimization server 20 generates a web page W1b by using the article contents C7 to C12 received from the content server 30 and the advertisement content AD1 received from the advertising device 100 (step S28). Then, the advertising device 100 distributes the generated web page W1b to the user terminal 10 (step S29). The user terminal 10 displays on the display screen what the web page W1b is connected to under the already displayed web page W1a as the web page W1.

[4. Advertising device configuration]
Next, the configuration of the advertising device 100 according to the first embodiment will be described with reference to FIG. FIG. 3 is a diagram showing a configuration example of the advertising device 100 according to the first embodiment. As shown in FIG. 3, the advertising device 100 includes a communication unit 110, an advertising information storage unit 120, and a control unit 130.

The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. Then, the communication unit 21 is connected to the network by wire or wirelessly, and transmits / receives information to / from the optimization server 20 and the content server 30.

The advertisement information storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory (Flash Memory), or a storage device such as a hard disk or an optical disk. The advertisement information storage unit 120 stores various information about the advertisement content received from the advertiser and the distribution record which is the result information when the advertisement content is distributed or clicked.

Here, FIG. 4 is a diagram showing an example of the advertisement information storage unit 120 according to the first embodiment. In the example of FIG. 4, the advertisement information storage unit 120 has items such as "advertiser ID", "advertisement content", "bid price", "CTR", and "eCPM".

The "advertiser ID" indicates identification information for identifying the terminal device (advertiser terminal) used by the advertiser or the advertiser for uploading advertisement contents. The "advertising content" indicates the advertising content submitted from the advertiser terminal 10. In FIG. 4, an example in which conceptual information such as “AD1” is stored in the “advertisement content” is shown, but in reality, images, videos, text data, URLs, file path names indicating their storage locations, etc. Is stored.

The "bid price" indicates the advertising price specified by the advertiser when uploading the advertising content. For example, the "bid price" corresponds to the unit price paid by the advertiser to the advertisement distributor (for example, the administrator of the advertising device 100) when the advertisement content is clicked once by the user.

“CTR” indicates a value obtained by dividing the number of times the advertisement content is clicked by the number of times the advertisement content is displayed. The CTR of the advertising content that has never been delivered to the terminal device 100 includes a predetermined fixed value, an average value of the CTR for all the advertising content, and the same advertising category (for example, car, travel). The average value of CTR and the like for all the advertising contents belonging to is stored. Further, the "CTR" may store a predicted CTR predicted from a CTR prediction model or the like. Such a predicted CTR is predicted by, for example, the type of advertising content, the type of web page on which the advertising content is displayed, and the like.

"ECPM" (effective cost per mille) indicates the expected return amount of the advertisement content around 1000 times displayed, and can be calculated by multiplying the CTR by the bid price, for example.

That is, FIG. 4 shows an example in which the advertiser identified by the advertiser ID “B1” submits the advertisement content “AD1” and specifies the bid price “150 yen”. Further, FIG. 4 shows an example in which the CTR of the advertising content “AD1” is “0.02” and the eCPM is “3 yen”.

Returning to FIG. 3, in the control unit 130, for example, various programs stored in the storage device inside the advertising device 100 are executed by the CPU (Central Processing Unit), the MPU (Micro Processing Unit), or the like using the RAM as a work area. It is realized by. Further, the control unit 130 is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 3, the control unit 130 includes a submission reception unit 131, a request reception unit 132, a calculation unit 133, an extraction unit 134, and a distribution unit 135, and the information processing described below includes the control unit 130. Realize or execute a function or action. The internal configuration of the control unit 130 is not limited to the information shown in FIG. 3, and may be any other configuration as long as it is configured to perform information processing described later. Further, the connection relationship of each processing unit included in the control unit 130 is not limited to the connection relationship shown in FIG. 3, and may be another connection relationship.

The submission reception unit 131 accepts submission of advertisement content from the advertiser terminal. Specifically, the submission reception unit 131 accepts submission of advertising content together with the designation of the bid price. Then, the submission reception unit 131 stores the received advertisement content and the bid price in the advertisement information storage unit 120 in association with the advertiser ID for the advertiser of the submission source.

The request receiving unit 132 receives an advertisement request from the optimization server 20. For example, the request reception unit 132 accepts an HTTP request as an advertisement request. In addition, the request receiving unit 132 receives information about the content to be distributed from the content server 30. For example, as shown in steps S14 and S24 of FIG. 2, the request receiving unit 132 sets the order of the article contents to be distributed from the content server 30 and the texts such as the title and description of the article contents to be distributed. , Accepts a list associated with each article content to be distributed.

The calculation unit 133 is displayed around the advertisement content of the distribution candidate, which is a candidate to be displayed, and the placement position of the advertisement content when the content and the advertisement content are displayed in a list as in the web page W1 shown in FIG. Calculate an index value that indicates the degree of relevance to the content. For example, the calculation unit 133 calculates the degree of similarity with the advertisement content of the distribution candidate for each content displayed around the arrangement position. Then, the calculation unit 133 calculates an index value with the content group displayed around the arrangement position by summing the calculated similarities. Hereinafter, the index value calculation process according to the first embodiment will be described with reference to FIG. FIG. 5 is a diagram showing an example of the index value calculation process according to the first embodiment. In the present embodiment, the arrangement position (display position) of the advertisement content and the article content indicates the arrangement order from the top when the advertisement content and the article content are arranged in a vertical row.

The web page W1x shown in FIG. 5 conceptually shows a part of the web page W1 which is the list information shown in FIG. 1 (a). Here, since the advertisement content arranged at the arrangement position Lx, which is the arrangement position of the advertisement content, that is, the advertisement content to be distributed is extracted by the extraction unit 134 described later, the calculation unit 133 is referred to as the advertisement content of the distribution candidate. The index value calculation process for calculating the index value indicating the degree of relevance to the article content will be described. The following two patterns can be considered for the index value calculation process.

First, pattern 1 will be described. As shown in FIG. 5, the placement position Lx of the advertisement content, that is, the arrangement order is the i-th. With this i-th as a reference, the placement position of the article content located above the placement position Lx can be determined as i-1st, i-2nd, i-3rd, and so on in order from the i-th. .. Further, the placement position of the article content located below the placement position Lx with the i-th as a reference can be determined as i + 1th, i + 2nd, i + 3rd, and so on in order from the i-th.

Here, the calculation unit 133 determines the article content from the placement position Lx to the upper and lower two articles content as the article content around the placement position Lx, and calculates the degree of similarity with the advertisement content I of the distribution candidate. That is, in the example of FIG. 5, the calculation unit 133 includes the distribution candidate advertisement content I, the i-2nd article content (article content B), the i-1st article content (article content C), and the i + 1th article content. The degree of similarity with the article content (article content D) and i + second article content (article content E) is calculated. Then, the calculation unit 133 calculates the index value between the advertisement content I and the article content group up to the upper and lower two from the arrangement position Lx by summing the calculated similarity.

The advertisement content I of the distribution candidate may indicate each advertisement content stored in the advertisement information storage unit 120 shown in FIG. 4, or is stored in the advertisement information storage unit 120 shown in FIG. It may indicate each advertisement content selected based on eCPM from each advertisement content.

The calculation unit 133 calculates the similarity based on the feature information indicating the features of the advertisement content and the article content. For example, the calculation unit 133 extracts a word (characteristic word) by morphological analysis of the text included in the advertisement content I, and generates a word vector indicating the characteristic of the advertisement content. Further, the calculation unit 133 extracts words (characteristic words) by morphological analysis of the texts included in each article content from the arrangement position Lx to the upper and lower two articles, and generates a word vector indicating the characteristics of each article content. To do. Then, the calculation unit 133 calculates the similarity between the generated word vectors (for example, the cosine similarity between the word vectors) for the advertisement content I and each article content. For example, the calculation unit 133 calculates a predetermined numerical value indicated in the range of "0 to 1" as the cosine similarity.

FIG. 5 shows an example in which the calculation unit 133 calculates the cosine similarity cos _i-2 as the similarity between the advertisement content I and the i-2nd article content B. Further, an example is shown in which the calculation unit 133 calculates the cosine similarity degree cos _i-1 as the degree of similarity between the advertisement content I and the i-1st article content C. The same applies to i + 1st article content D and i + 2nd article content E.

In addition, the calculation unit 133 adds a predetermined weight value to each calculated similarity. For example, in the pattern 1, the calculation unit 133 multiplies the article content from the arrangement position Lx to the upper and lower two article contents by a weight value having a higher degree of similarity to the article content closer to the arrangement position Lx. In the present embodiment, the weight value r, which is the highest weight value, is set to "0.9".

In the example of FIG. 5, since the i-1st article content C and the i + 1st article content D are adjacent to the placement position Lx, these article contents are closest to the placement position Lx. Therefore, calculation unit 133, the similarity _{cos i + 1} of the similarity _{cos i-1} and ad content I and the (i + 1) th article content D of the advertisement content I and i-1 th article content C, the weight value r Multiply by (0.9).

On the other hand, the i-2nd article content B and the i + 2nd article content E are separated by one content from the arrangement position Lx. Therefore, calculation unit 133, the similarity _{cos i + 2} the similarity _{cos i-2} and ad content I and i + 2-th article content E of the advertising content I and i-2-th article content B, the weight value r Multiply the smaller weight value r ² (0.81).

For example, by arranging the advertisement content more similar to the arrangement position Lx and the latest article content at the arrangement position Lx, it is considered that the user's interest in the arranged advertisement content can be enhanced. This is because whether or not a user is interested in advertising content tends to be more influenced by the content of the latest article content. For example, when the article contents C and D are sports-related articles, by arranging the sports-related advertisement contents at the placement position Lx, the article contents C and D increase the user's interest in sports and are sports-related. It will be easier to click because you are also interested in the advertising content of.

In consideration of such user characteristics, as described above, the calculation unit 133 multiplies an advertisement similar to the article content close to the placement position Lx by a weight value higher as the similarity with the article content close to the placement position Lx. Content can be easily extracted.

The calculation unit 133, by summing the similarity multiplied by the weight value, calculating advertising content I, the index value S _I indicating the relevance of the article content group to be displayed in the peripheral position Lx .. Specifically, in the index value calculation process in the Pattern 1 described so far, the calculation unit 133 can calculate the index value S _I by the following equation (1).

Index value ^{_{S I = r 2 cos i-}} 2 + rcos i-1 + rcos i + 1 + r 2 cos i + 2 ··· (1)

That is, the calculating unit 133, for each advertising content of each distribution candidate, using equation (1), calculates an index value S _I indicating the relevance of the article content group from position Lx up to two minutes up and down ..

Then, calculating unit 133, based on the index value S _I calculated using Equation (1), calculates an advertisement evaluation value. For example, calculator 133 calculates the eCPM _I is an evaluation value of the advertising content I, the sum of the index value _{S I} calculated using Equation (1) as an ad evaluation value _{E I.} Specifically, the calculation unit 133 by the following equation (2) to calculate the advertisement evaluation value _{E I.}

Advertisement evaluation value _{E I} = eCPM I + index value _S I ··· (2)

That is, the calculating unit 133, for each advertising content of each distribution candidate, using equation (2), calculates an advertisement evaluation value E _I.

Next, pattern 2 will be described. Pattern 2 is different from pattern 1 in the way weight values are assigned. Other points are the same as in pattern 1. Specifically, in pattern 1, an example is shown in which the calculation unit 133 multiplies a weight value higher by the degree of similarity with the article content closer to the arrangement position Lx. However, the calculation unit 133 multiplies the weight value as high as the similarity with the article content located closer to the placement position Lx by the higher the similarity with the article content located above the placement position Lx.

For example, the calculation unit 133 includes the i-1st article content C located closest to the placement position Lx and upward of the placement position Lx, and the advertisement content I, as shown in pattern 2 shown in FIG. Multiply the similarity cos _i-1 by the highest weight value r (0.9). Further, the calculation unit 133 sets the similarity between the i-2nd article content B, which is next to the placement position Lx and is located above the placement position Lx, and the advertisement content I to cos _i-2 . Multiply the highest weight value r ² (0.81).

Further, the calculation unit 133 has a weight value r that is the third highest in the similarity cos _{i + 1} between the i + 1st article content D located closest to the placement position Lx and downward of the placement position Lx and the advertisement content I. Multiply by ³ (0.73). Further, the calculation unit 133 has the fourth highest weight in the similarity cos _{i + 2} between the i + 2nd article content E, which is next to the placement position Lx and is located in the lower direction of the placement position Lx, and the advertisement content I. Multiply the value r ⁴ (0.66).

So far, it has been described that by arranging the advertisement content more similar to the arrangement position Lx and the latest article content at the arrangement position Lx, the user's interest in the arranged advertisement content can be enhanced. However, when browsing the list information in which a plurality of contents are arranged in a vertical row as in the web page W1 according to the first embodiment, the user scrolls the web page W1 upward to browse each content. It is thought that it is often browsed.

In such a case, whether or not the user is interested in the advertising content is influenced by the content of the latest article content, and the web page W1 is scrolled upward to be noticed by the user earlier. It is thought that there is a tendency to be easily influenced by the content of the article content. For example, when the article content C is a sports-related article and the article content D is a fashion-related article, the sports-related advertisement content is placed rather than the fashion-related advertisement content placed at the placement position Lx. , Sports-related article content C, which was noticed before fashion-related article content D, enhances the user's interest in sports, and makes it easier for users to be interested in sports-related advertising content and click on it.

In consideration of such user characteristics, the calculation unit 133 multiplies the placement position Lx by a weight value that is close to the placement position Lx and has a higher degree of similarity to the article content located in the upward direction of the placement position Lx. It is possible to facilitate the extraction of advertising content similar to the article content located close to and above the placement position Lx.

The calculation unit 133, by summing the similarity multiplied by the weight value, and advertising content I, the index value S _I from the position Lx indicates the relevance of the articles content group up to 2 pieces of the upper and lower calculate. Specifically, in the index value calculation process in the Pattern 2 described so far, the calculation unit 133 can calculate the index value S _I by the following equation (3).

Index value ^{_{S I = r 2 cos i-}} 2 + rcos i-1 + r 3 cos i + 1 + r 4 cos i + 2 ··· (3)

That is, the calculating unit 133, for each advertising content of each distribution candidate, using equation (3), calculates an index value S _I indicating the relevance of the article content group from position Lx up to two minutes up and down ..

Then, calculating unit 133, based on the index value S _I calculated using Equation (3) to calculate the advertisement evaluation value. For example, calculator 133, and eCPM _I advertising content I, using equation (3), and calculates the sum of the index value _{S I} calculated for ad content I as an advertisement evaluation value _{E I.} In other words, calculation unit 133, the above equation (2) to calculate the advertisement evaluation value _{E I.}

Returning to FIG. 3, the extraction unit 134 extracts the advertisement content to be distributed from the advertisement content of the distribution candidate based on the index value calculated by the calculation unit 133. For example, the extraction unit 134 extracts the advertisement content of the distribution candidate having the highest advertisement evaluation value calculated by using the above formula (2) as the distribution target by the calculation unit 133.

The distribution unit 135 distributes the advertisement content to be distributed. Specifically, the distribution unit 135 distributes the advertisement content to be distributed extracted by the extraction unit 134 to the optimization server 20.

[5. Specific example of advertisement extraction process]
By the way, in the following, the advertisement extraction process conceptually described with reference to FIG. 5 will be described with reference to a specific example. FIG. 6 is an explanatory diagram for specifically explaining the advertisement extraction process according to the first embodiment.

First, it is assumed that the user terminal 10 transmits a request for the web page W1a, which is the initially displayed part of the web page W1, to the optimization server 20 according to the user operation. Further, as a result, as shown in FIG. 6, the content server 30 determines that the article content to be distributed is the article content C1 to C6, so that the list 1 in which the order and the text information T1 to T6 are associated with each other is displayed. It is assumed that the information is transmitted to the advertising device 100. Further, when the advertisement device 100 receives the list 1, the advertisement content of the advertisement content stored in the advertisement information storage unit 120 shown in FIG. 4 is distributed with the top three advertisement contents AD1 to AD3 having high eCPM. Suppose that it is decided as.

In the web page W1a, as described above, it is assumed that it is predetermined to insert the advertisement content at the arrangement position L1 (fourth from the top) which is an intermediate position.

Here, the calculation unit 133 of the advertising device 100 calculates the degree of similarity between the article contents C2 to C5, which are the article contents displayed around the arrangement position L1, with the advertisement contents AD1 to AD3 of the distribution candidates.

For example, when the pattern 1 shown in FIG. 5 is used, the distribution candidate advertisement content AD3 will be described as an example. For example, the calculation unit 133 will set “0” as the similarity cos _i-2 between the advertisement content AD3 and the article content C2. .3 "," 0.8 "as the degree of similarity _{cos i-1} of the advertising content AD3 and article content C3," 0.8 "as the degree of similarity _{cos i + 1} of the advertising content AD3 and article content C4, and advertising content AD3 "0.1" is calculated as the degree of similarity cos _{i + 2} with the article content C5.

As shown in FIG. 6, the advertisement content AD3 is a sports-related advertisement, and the article content C2 is a fashion-related article. Since the similarity between sports and fashion is low, the calculation unit 133 uses the feature words extracted from the text "Large sports shop SS Japan's first landing !!" in the advertising content AD3 and the text T2 "Style T2" in the article content C2. For example, a low "0.3" is calculated as the cosine similarity cos _i-2 with the feature word extracted from "self-portrait tech".

On the other hand, since the article contents C3 and C4 are sports-related articles and have high similarity to the advertisement content AD3, the calculation unit 133 uses the feature words extracted from the text of the advertisement content AD3 and the text T3 “Pro” of the article content C3. For example, a higher "0.8" is calculated as the cosine similarity cos _i-1 with the feature words extracted from "Baseball News Highlights". In addition, the calculation unit 133, as the cosine similarity cos i + ₁ between the feature words extracted from the text T4 of characteristic words and the article content C4 extracted from the text of the ad content AD3 "is an issue that stands out Japan Women's Valley?", Similar In addition, a higher "0.8" is calculated.

Further, since the article content C5 is a political-related article and has low similarity to the advertisement content AD3, the calculation unit 133 calculates, for example, "0.1" which is lower than the article content C2 as the similarity cos _{i + 2.} ..

Then, the calculation unit 133 multiplies each calculated similarity by a weight value. For example, the calculation unit 133 multiplies a weight value higher by the degree of similarity with the article content located near the arrangement position L1 according to the pattern 1 shown in FIG.

Then, the calculation unit 133 applies each degree of similarity multiplied by the weight value to the above equation (1), so that the advertisement content AD3 of the distribution candidate and the article contents C2 to C5 displayed around the arrangement position L1 The index value S _AD3 is calculated. Specifically, the calculation unit 133 uses the above formula (1) to indicate the index value S _AD3 = (0.81 × 0.3) + (0.9 × 0.8) + (0.9 × 0). 8.8) + (0.81 × 0.1) = 1.764 is calculated.

Further, as shown in the above formula (2), the calculation unit 133 sums the eCPM _AD3 "2.2" of the advertisement content AD3 and the index value S _AD3 "1.764" to advertise the advertisement content AD3. "3.9764" is calculated as the evaluation value E _AD3 .

Up to this point, using FIGS. 5 and 6, the calculation unit 133 calculates the index value S _AD3 and the advertisement evaluation value E _AD3 of the advertisement content AD3 and the article contents C2 to C5 displayed around the placement position L1. An example is shown. Similarly, the calculation unit 133 calculates "0.863" as the index value S _AD1 and "3.863" as the advertisement evaluation value E _AD1 for the advertisement content AD1 of the distribution candidate. Further, the calculation unit 133 similarly calculates “1.278” as the index value S _AD2 and “2.328” as the advertisement evaluation value E _AD2 for the advertisement content AD2 of the distribution candidate.

Next, the extraction unit 134 extracts the advertisement content AD3 for which the highest advertisement evaluation value is calculated among the index values calculated by the calculation unit 133 as the distribution target. Then, in order to distribute the advertisement content AD3 to the optimization server 20, the distribution unit 135 distributes the web page W1a in which the advertisement content AD3 is arranged at the arrangement position L1 by the optimization server 20.

For example, in the case of general advertisement distribution, it is conceivable that the advertisement content having the highest eCPM is simply extracted as the distribution target. In this case, in the example of FIG. 6, the advertisement content AD1 is the distribution target. However, as in the present embodiment, when the advertisement content to be distributed is further extracted based on the index value of the advertisement content to be distributed and the article content around the placement position, it is distributed when only eCPM is considered. The target may be different.

The advertising content to be delivered extracted in this way has a relatively high eCPM and has a high affinity with the article content around the position, so that the advertising effect is higher than that of the advertising content extracted based on the eCPM. Can be generated.

[6. Processing procedure]
Next, with reference to FIG. 7, the procedure of the advertisement extraction process executed by the advertisement device 100 according to the first embodiment will be described. FIG. 7 is a flowchart showing an advertisement extraction processing procedure by the advertisement device 100 according to the first embodiment.

First, the request receiving unit 132 of the advertising device 100 determines whether or not the advertising request has been received from the optimization server 20 (step S101). When the request receiving unit 132 receives the advertisement request (step S101; Yes), the request receiving unit 132 determines whether or not the list related to the article content has been received from the content server 30 (step S102). If the request receiving unit 132 has received the list (step S102; Yes), the request receiving unit 132 transmits the received list to the calculation unit 133.

Here, the list related to the article content is a list in which the order of the article content to be distributed and the text information are associated with each advertisement content to be distributed, as described above. Further, the request receiving unit 132 may perform steps S101 and S102 at the same time, or may be configured to receive, for example, an advertisement request including a list from the content server 30.

Next, the calculation unit 133 refers to the received list and specifies the article content displayed around the arrangement position Lx where the advertisement content is arranged (step S103). For example, the calculation unit 133 specifies the article contents displayed up to two above and below the placement position Lx as the article contents displayed around the placement position Lx.

In addition, the calculation unit 133 determines the advertisement content of the distribution candidate (step S104). For example, the calculation unit 133 refers to the advertisement information storage unit 120 and determines a high-order predetermined number of advertisement contents having a high eCPM as the advertisement contents of the distribution candidate.

Then, the calculation unit 133 selects one from the advertisement contents of the distribution candidates (step S105). Here, the selected advertising content is designated as advertising content I. Then, the calculation unit 133 calculates the degree of similarity with the advertisement content I for each article content displayed around the arrangement position Lx (step S106). Further, the calculation unit 133 weights each calculated similarity (step S107). For the weighting, either pattern 1 or pattern 2 described with reference to FIG. 5 may be used.

The calculation unit 133, by summing the similarity is weighted to calculate the advertising content I, the index value S _I of the article content group to be displayed in the peripheral position Lx (step S108). For example, in step S107, when weighted using the pattern 1, the calculation unit 133 calculates an index value _{S I} using equation (1). Furthermore, when weighted with the pattern 2, the calculation unit 133 calculates an index value S _I using equation (3).

Further, calculator 133, by summing the eCPM and the index value _{S I} of the advertising content I, calculates an advertisement evaluation value _{E I} (step S109). Thereafter, the calculation unit 133, the advertisement content all delivery candidates, determines whether to calculate the advertisement evaluation value E _I (step S110). Then, calculating unit 133, the advertisement content all delivery candidates, when it is determined that the calculated advertisement evaluation value _{E I;} send (step S110 Yes), the calculation result to the extraction unit 134.

Next, the extraction unit 134 receives a calculation result, by comparing the advertisement contents each ad evaluation value E _I distribution candidate, extracts the highest advertising content of the advertisement evaluation value E _I as a delivery target (step S111 ). The distribution unit 135 distributes the extracted advertisement content to the optimization server 20 (step 112).

[7. Modification example]
The first embodiment described above may be implemented in various different forms other than the above-described embodiment. Therefore, other embodiments will be described below.

[7-1. Category classification]
In the first embodiment, as an example of calculating the similarity with the advertisement content for each article content by the calculation unit 133 of the advertisement device 100, the feature word extracted from the text of the advertisement content and the text of the article content are extracted. An example of calculating the cosine similarity with the featured words is shown. However, the calculation unit 133 may calculate the similarity (category similarity) between the category to which the advertisement content of the distribution candidate belongs and the category to which the article content displayed around the placement position belongs. This point will be described with reference to FIG. See also FIGS. 5 and 6 as appropriate.

FIG. 8 is a diagram showing an example of categorization according to the modified example in the first embodiment. As shown in FIG. 8, the categorization is divided into a plurality of layers in a tree format. The first layer is a major classification and corresponds to the widest category classification. The second layer is a middle classification, and corresponds to a more subdivided category classification of each category of the first layer. The third layer is a sub-classification, and corresponds to a more subdivided category classification of each category of the second layer.

Here, in the above, as shown in the formula (1), the calculation unit 133 calculates the index value by summing the cosine similarity weighted by the pattern 1, or as shown in the formula (3). , An example of calculating an index value by summing each cosine similarity weighted by pattern 2 is shown. Even when the category similarity is used, the calculation unit 133 calculates the index value by summing each category similarity weighted by pattern 1, or totals each category similarity weighted by pattern 2. Therefore, the index value can be calculated.

Specifically, when each category similarity is weighted in pattern 1, the calculation unit 133 uses the following formula (4) to express the advertisement content I to be delivered and the article content group displayed around the placement position Lx. it is possible to calculate the index value S _I of.

Index value ^{_{S I = r 2 CG i-}} 2 + rCG i-1 + rCG i + 1 + r 2 CG i + 2 ··· (4)

With reference to FIG. 5, “CG _i-2 ” indicates the categorical similarity between the advertisement content I and the i-2nd article content B. “CG _i-1 ” indicates the categorical similarity between the advertising content I and the i-1st article content C. “CG _{i + 1} ” indicates the category similarity between the advertisement content I and the i + 1th article content D. “CG _{i + 2} ” indicates the category similarity between the advertisement content I and the i + second article content E.

Below, a specific example of calculating the similarity using the category tree shown in FIG. 8 is shown. For example, as shown in FIG. 6, the advertising device 100 accepts the list 1 in which the order of the article contents to be distributed and the text information are associated with each other, and determines the advertising contents AD1 to AD3 as the advertisement contents of the distribution candidates. And.

Here, the calculation unit 133 of the advertising device 100 calculates the category similarity with each of the distribution candidate advertisement contents AD1 to AD3 for each of the article contents C2 to C5 which are the article contents displayed around the arrangement position L1.

For example, to explain the distribution candidate advertisement content AD3 as an example, when calculating the category similarity CG _i-2 between the advertisement content AD3 and the article content C2, as shown in FIG. 6, the fourth (i) advertisement. The content AD3 includes a text such as "Large sports shop SS Japan's first landing !!". Therefore, the calculation unit 133 specifies, for example, the category of the advertisement content AD3 as "sports". In addition, the second (i-2) article content C2 includes a text such as "selfie tech that shows the style well". Therefore, the calculation unit 133 specifies, for example, the category of the article content C2 as "fashion".

Here, according to the category tree shown in FIG. 8, since "sports" and "fashion" are categories that can be roughly classified, it can be said that they are not very similar. When calculating the similarity between categories of such major categories, the calculation unit 133 subtracts "0.5" from the maximum value "1" of the similarity, and sets "sports" and "fashion". The degree of similarity, that is, the degree of similarity "0.5" between the advertisement content AD3 and the article content C2 is calculated.

Further, when calculating the category similarity CG _i-1 between the advertisement content AD3 and the article content C3, as shown in FIG. 6, the third (i-1) article content C3 is "Professional baseball news highlight". Includes text such as. Therefore, the calculation unit 133 specifies, for example, the category of the article content C3 as "professional baseball".

According to FIG. 8, since “professional baseball” is a category that falls under the category of “sports”, it can be said that the two have a relatively high degree of similarity. And, "sports" and "professional baseball" are separated by two levels. In such a case, for example, the calculation unit 133 adjusts the maximum value "1" of the similarity using "0.1" in order to follow one layer, and the maximum value "1" of the similarity is changed to "1". "0.1 x 2 (for 2 layers)" is subtracted. Then, the calculation unit 133 calculates the degree of similarity between "sports" and "professional baseball", that is, the degree of similarity "0.8" between the advertisement content AD3 and the article content C3.

Further, when calculating the category similarity CG _{i + 1} between the advertisement content AD3 and the article content C4, as shown in FIG. 6, the fifth (i + 1) article content C4 is "What is the problem that emerged in the Japan Women's Valley?" Includes text such as. Therefore, the calculation unit 133 specifies, for example, the category of the article content C4 as "valley".

According to FIG. 8, since “valley” is a category that falls under the category of “sports”, it can be said that the two have a relatively high degree of similarity. And, "sports" and "valley" are separated by one level. In such a case, the calculation unit 133 subtracts "0.1 (for one layer)" from the maximum value "1" of the similarity, for example. Then, the calculation unit 133 calculates the degree of similarity between "sports" and "valley", that is, the degree of similarity "0.9" between the advertisement content AD3 and the article content C4.

Further, when calculating the category similarity CG _{i + 2} between the advertisement content AD3 and the article content C5, as shown in FIG. 6, the sixth (i + 2) article content C5 is said to be "the joint exercise between the United States and South Korea is completed". Includes text. Therefore, the calculation unit 133 specifies, for example, the category of the article content C5 as "politics".

According to FIG. 8, since "sports" and "politics" are categories that can be roughly classified, it can be said that they are not very similar. Therefore, for example, the calculation unit 133 subtracts "0.5" from the maximum value "1" of the similarity to obtain the similarity between "sports" and "politics", that is, the advertisement content AD3 and the article content C2. The similarity "0.5" of is calculated.

Then, the calculation unit 133 multiplies the calculated similarity of each category by the weight value. For example, the calculation unit 133 multiplies a weight value higher by the degree of similarity with the article content located near the arrangement position L1 according to the pattern 1 shown in FIG.

Then, the calculation unit 133 applies each degree of similarity multiplied by the weight value to the above equation (4), thereby causing the advertisement content AD3 of the distribution candidate and the article contents C2 to C5 displayed around the placement position L1. The index value S _AD3 is calculated. Specifically, the calculation unit 133 uses the above equation (4) to indicate the index value S _AD3 = (0.81 × 0.5) + (0.9 × 0.8) + (0.9 × 0). .9) + (0.81 x 0.5) = 2.34 is calculated.

Further, as shown in the above formula (2), the calculation unit 133 sums the eCPM _AD3 "2.2" of the advertisement content AD3 and the index value S _AD3 "2.34" to advertise the advertisement content AD3. "4.54" is calculated as the evaluation value E _AD3 .

Up to this point, the calculation unit 133 has shown an example of calculating the index value S _AD3 and the advertisement evaluation value E _AD3 of the advertisement content AD3 and the article contents C2 to C5 displayed around the arrangement position L1. Similarly, the calculation unit 133 calculates the index value S _AD1 and the advertisement evaluation value E _AD1 from the category similarity with each of the article contents C2 to C5 for the advertisement content AD1 to be distributed. Further, the calculation unit 133 similarly calculates the index value S _AD2 and the advertisement evaluation value E _AD2 from the category similarity with each of the article contents C2 to C5 for the advertisement content AD2 to be distributed.

Further, when each category similarity is weighted by the pattern 2 shown in FIG. 5, the calculation unit 133 uses the following formula (5) to display the advertisement content I to be delivered and the article content displayed around the placement position Lx. it is possible to calculate the index value S _I with the group.

Index value ^{_{S I = r 2 CG i-}} 2 + rCG i-1 + r 3 CG i + 1 + r 4 CG i + 2 ··· (5)

In this way, the advertising device 100 according to the modified example of the first embodiment calculates the category similarity with the advertisement content of the distribution candidate for each article content displayed around the arrangement position, and calculates the calculated similarity. Use to calculate the index value. As a result, the advertising device 100 can specify the category between the advertising content and the article content and calculate the category similarity by using the category tree as shown in FIG. 8, so that the feature word extraction by text analysis and the like can be performed. It is not necessary to perform this, and the process of calculating the advertisement evaluation value can be speeded up as compared with the case of calculating the cosine similarity shown in FIG.

[8. effect〕
The advertising device 100 according to the first embodiment has a calculation unit 133 and an extraction unit 134. The calculation unit 133 calculates an index value indicating the degree of relevance between the advertisement content of the distribution candidate displayed in a list together with the content and the content displayed around the arrangement position where the advertisement content of the distribution candidate is arranged. The extraction unit 134 extracts the advertisement content to be distributed from the advertisement content of the distribution candidate based on the index value calculated by the calculation unit 133.

As a result, the advertising device 100 according to the first embodiment can display the advertising content having a higher affinity with the content displayed around the arrangement position on the user terminal 10, so that the advertising effect can be enhanced. ..

Further, the calculation unit 133 calculates the similarity with the advertisement content of the distribution candidate for each content displayed around the placement position, and uses each of the calculated similarities with the content group displayed around the placement position. Calculate an index value that indicates the degree of relevance to the advertisement content of the delivery candidate.

In this way, the advertising device 100 according to the first embodiment calculates the similarity with the advertisement content of the distribution candidate for each content displayed around the placement position, so that the content displayed around the placement position It is possible to accurately calculate an index value indicating the degree of relevance between the group and the advertisement content of the distribution candidate.

Further, the calculation unit 133 weights the contents displayed around the arrangement position as having a higher degree of similarity to the contents closer to the arrangement position.

As a result, the advertising device 100 according to the first embodiment calculates an index value in consideration of user characteristics such that whether or not the user is interested in the advertising content is easily affected by the content closer to the placement position. Therefore, it is possible to display the advertisement content having a high affinity with the content closer to the arrangement position on the user terminal 10. As a result, the advertising device 100 can enhance the effect.

In addition, the calculation unit weights the content displayed around the arrangement position as having a higher degree of similarity to the content located above the arrangement position.

As a result, in the advertising device 100 according to the first embodiment, whether or not the user is interested in the advertising content is easily affected by the content located closer to the placement position and upward from the placement position. Since the index value can be calculated in consideration of the user characteristics, the user terminal 10 can display the advertising content that is closer to the placement position and has a high affinity with the content located above the placement position. As a result, the advertising device 100 can enhance the effect.

In addition, the calculation unit 133 calculates the degree of similarity between the information extracted from the text included in the advertisement content of the distribution candidate and the information extracted from the text included in the content displayed around the placement position.

As described above, since the advertising device 100 according to the first embodiment calculates the similarity using the information extracted from the text, the similarity can be calculated accurately.

In addition, the calculation unit 133 calculates the degree of similarity between the category to which the advertisement content of the distribution candidate belongs and the category to which the content displayed around the placement position belongs.

As described above, the advertising device 100 according to the first embodiment extracts from the text in order to calculate the similarity by comparing the category to which the advertising content belongs with the category to which the content displayed around the arrangement position belongs. The processing speed can be increased as compared with the case of calculating the similarity using the obtained information.

Further, the calculation unit 133 calculates an index value indicating the degree of relevance by summing the similarity, and the extraction unit 134 is the sum of the index value calculated by the calculation unit 133 and the evaluation value of the content of the distribution candidate. Based on, the advertisement content to be distributed is extracted from the advertisement content of the distribution candidate.

As a result, the advertising device 100 according to the first embodiment can enhance the advertising effect.

(Second Embodiment)
[1. Advertising device configuration]
By the way, in the first embodiment, the calculation unit 133 of the advertising device 100 calculates the similarity with the advertisement content of the distribution candidate for each article content around the placement position, and uses the calculated similarity to calculate the index value. An example of calculation has been described. However, in the list information in which the article content and the advertisement content are displayed in a list like the web page W1, the article content and the advertisement content that the user is interested in are predicted, and it is predicted that the user is interested. Processing such as facilitating the extraction of advertising content having a high affinity with the content may be performed.

Then, in the following, the advertising device 200 in which the above-mentioned advertising device 100 is further configured to perform such a prediction process will be described. FIG. 9 is a diagram showing a configuration example of the advertising device 200 according to the second embodiment. As shown in FIG. 9, the advertising device 200 includes a communication unit 110, an advertising information storage unit 120, and a control unit 230.

Further, as shown in FIG. 9, the control unit 230 includes a submission reception unit 131, a request reception unit 132, a calculation unit 133, an extraction unit 134, a distribution unit 135, and a prediction unit 236. That is, the advertising device 200 corresponds to a device in which the prediction unit 236 is further added to the advertising device 100.

The prediction unit 236 predicts the article content and the advertisement content that the user is interested in among the contents included in the web page W1. For example, the prediction unit 236 predicts article content and advertisement content that the user is interested in by analyzing the user's operation log transmitted from the user terminal 10.

For example, the prediction unit 236 calculates the moving speed at which the web page W1 is moved by the user operation on the web page W1. Then, the prediction unit 236 identifies the content located near the center of the display screen of the user terminal 10 when the moving speed becomes equal to or lower than the predetermined speed, and predicts that the user is interested in the specified content. To do.

For example, when the user is browsing each content while scrolling the web page W1, if the content of interest is noticed, the user unknowingly slows down the scrolling speed or stops the scrolling operation. It is believed that there is. Based on such characteristics, the prediction unit 236 predicts that the user is interested in the content located near the center of the display screen of the user terminal 10 when the moving speed becomes equal to or lower than the predetermined speed. .. The prediction unit 236 does not necessarily have to predict that the user is interested in the content located near the center of the display screen, and may be at any position on the display screen.

Further, for example, when the user is browsing each content while scrolling the web page W1, if there is content that is of interest, the user selects the content and transitions to the detail page. Therefore, the prediction unit 236 may predict that the content selected by the user among the contents included in the web page W1 is the content that the user is interested in.

Then, the calculation unit 133 gives a high weight to the similarity with the article content predicted to be of interest to the user by the prediction unit 236, and the weighted similarity is placed with the advertisement content I to be delivered. The index value _Si is calculated by adding the similarity to each article content displayed in the periphery to each weighted similarity as shown in the above pattern 1 or 2.

For example, if the cosine similarity between the article content Y and the advertisement content I predicted to be of interest to the user by the prediction unit 236 is cos _Y , the calculation unit 133 sets the cosine similarity to cos _Y most. Multiply the high weight value r (0.9). Then, calculating unit 133, the case of using the pattern 1, the following equation (6), calculates an index value _{S I.}

Index value ^{_{S I = (r 2 cos i}} -2 + rcos i-1 + rcos i + 1 + r 2 cos i + 2) + rcos Y ··· (6)

The formula in parentheses corresponds to the above formula (1). That is, the calculation unit 133 calculates rcos _Y, which is obtained by multiplying the cosine similarity cos _Y between the article content Y and the advertisement content I predicted to be of interest to the user by the prediction unit 236 by the highest weight value r. calculating an index value S _I using equation (6), further added to the above formula (1). From this, the calculation unit 133 makes it easier to extract the advertisement content having a high affinity with the article content Y as the distribution target by increasing the influence degree of the cosine similarity cos _Y.

Further, calculator 133, the case of using the pattern 2, the following equation (7), calculates an index value _{S i.}

Index value ^{_{S I = (r 2 cos i}} -2 + rcos i-1 + r 3 cos i + 1 + r 4 cos i + 2) + rcos Y ··· (7)

The formula in parentheses corresponds to the above formula (3). Further, as shown in equation (6) or expression (7), an example of calculating an index value S _i using the cosine similarity may be a category similarity.

[2. Data flow]
Next, with reference to FIG. 10, the advertisement extraction process by the advertisement extraction system 2 according to the second embodiment will be described while clarifying the data flow. FIG. 10 is a diagram showing an example of an advertisement extraction process by the advertisement extraction system 2 according to the second embodiment.

First, it is assumed that the web page W1 including the web pages W1a and W1b is displayed on the user terminal 10. In such a state, the user terminal 10 acquires a user operation on the web page W1 and a display mode of the web page W1 changed in response to the user operation as an operation log (step S31).

Here, it is assumed that the user terminal 10 transmits the request of the web page W1c connected under the web page W1b and the operation log acquired in step S31 to the optimization server 20 according to the user operation (step S32). When the optimization server 20 receives the request of the web page W1c, the optimization server 20 sends a content request for acquiring the article content included in the web page W1c to the content server 30, and also acquires the advertisement content included in the web page W1a. The advertisement request and the operation log are transmitted to the advertisement device 200 (step S33).

When the content server 30 receives the content request from the optimization server 20, the content server 30 determines the order of the article content to be distributed and the article content to be distributed (step S34). In addition, the content server 30 generates a list 3 that lists the determined information. Listing 3 shown in FIG. 10 shows that the content server 30 has decided to arrange the article contents C13 to C18 to be distributed in a vertical row such as the 15th, 16th, ... 21st from the top. Further, an example is shown in which the content server 30 associates text information such as a title and a description with each article content to be distributed.

The content server 30 transmits the list 3 generated in this way to the advertising device 200 (step S35). Further, as shown in Listing 3, the content server 30 associates the data of the article content to be distributed with the arrangement order and transmits the data to the optimization server 20 (step S36).

On the other hand, when the request receiving unit 132 receives the advertisement request and the operation log from the optimization server 20, the prediction unit 236 of the advertising device 200 refers to the operation log and predicts the content that the user is interested in. (Step S34). For example, the prediction unit 236 calculates the moving speed at which the web page W1 is moved, and when the moving speed becomes equal to or less than a predetermined speed, the user can use the content located near the center of the display screen of the user terminal 10. Predict the content you are interested in. Further, for example, the prediction unit 236 may predict the content selected by the user as the content that the user is interested in. Here, it is assumed that the prediction unit 236 predicts that the user is interested in the article content C11.

Further, the calculation unit 133 of the advertisement device 200 refers to the list 3 received from the optimization server 20 by the request reception unit 132, and has the advertisement content of the distribution candidate, the article content displayed around the arrangement position L3, and the interest. An index value indicating the degree of relevance to the article content C11 predicted to be is calculated. In addition, the calculation unit 133 calculates the advertisement evaluation value, which is the sum of the index value and the eCPM. Then, the extraction unit 134 compares the calculated advertisement evaluation values of the distribution candidates and extracts the advertisement content to be distributed (step S36). Here, it is assumed that the extraction unit 134 has extracted the advertisement content AD2.

Then, the distribution unit 135 of the advertisement device 200 transmits the extracted advertisement content AD2 to the optimization server 20 (step S37). The optimization server 20 generates a web page W1c by using the article contents C13 to C18 received from the content server 30 and the advertisement content AD2 received from the advertising device 200 (step S38). Then, the optimization server 20 distributes the generated web page W1c to the user terminal 10 (step S39). The user terminal 10 displays on the display screen a web page W1 in which the web page W1c is connected under the already displayed web page W1b.

As described above, the advertising device 200 according to the second embodiment calculates an index value further considering the similarity with the content predicted to be of interest to the user, and distributes the index value based on the calculated index value. Extract the target advertising content. As a result, the advertising device 200 can easily display the advertising content having a high affinity with the article content that the user is interested in, so that the advertising effect can be enhanced.

(Third Embodiment)
[1. Advertisement extraction process by terminal device]
In each of the above embodiments, the advertising devices 100 and 200 calculate an index value indicating the degree of relevance between the advertisement content of the distribution candidate and the content displayed around the arrangement position where the advertisement content of the distribution candidate is arranged, and the index value. An example of extracting the advertisement content to be delivered based on the value has been described. However, such an advertisement extraction process may be performed by the user terminal 10 which is an example of the terminal device. Hereinafter, the advertisement extraction process by the user terminal 10 will be described. Since the advertisement extraction process by the user terminal 10 is the same as the advertisement extraction process performed by the advertisement devices 100 and 200, detailed description thereof will be omitted.

The configuration of the advertisement extraction system 3 according to the third embodiment will be described with reference to FIG. FIG. 11 is a diagram showing a configuration example of the advertisement extraction system 3 according to the third embodiment. As shown in FIG. 11, the advertisement extraction system 3 includes a user terminal 10, an optimization server 20, a content server 30, and advertisement servers 50a to 50c. The user terminal 10, the optimization server 20, the content server 30, and the advertising servers 50a to 50c are connected to each other via a network so as to be communicable by wire or wirelessly. The advertisement extraction system 3 shown in FIG. 11 may include a plurality of user terminals 10, a plurality of optimization servers 20, and a plurality of content servers 30. Further, in the example shown in FIG. 11, the advertisement extraction system 3 includes three advertisement servers, but it is not necessary to be limited to three, and the advertisement extraction system 3 includes more advertisement servers. It may be 3 or less.

The user terminal 10 is a terminal device used by the user, and performs an advertisement extraction process based on the index value calculation performed by the advertisement devices 100 and 200 described above.

When the advertisement servers 50a to 50c receive the advertisement request, the advertisement contents are extracted from a predetermined storage unit in the own device, and the extracted advertisement contents are delivered to the optimization server 20.

Further, as shown in FIG. 11, the content server 30 is used by the distributor t1, the advertisement server 50a is used by the distributor t2, the advertisement server 50b is used by the distributor t3, and the advertisement server 50c is used. Used by distributor t4. Further, the distributors t1 to t4 are different distributors.

Next, with reference to FIG. 11, the advertisement extraction process by the advertisement extraction system 3 according to the third embodiment will be described while clarifying the data flow.

First, it is assumed that the user terminal 10 transmits a request for the web page W1a, which is the initially displayed portion of the web page W1, to the optimization server 20 according to the user operation (step S40). When the optimization server 20 receives the request of the web page W1a, the optimization server 20 transmits the content request for acquiring the article content included in the web page W1a to the content server 30 (step S41), and sends the advertisement request to the advertisement server 50a to the advertisement server 50a. It is transmitted to each of 50c (step S41).

When the content server 30 receives a content request from the optimization server 20, for example, the content server 30 refers to a predetermined storage unit in its own device that stores various article contents, and the article content to be distributed and the article content to be distributed. The order is determined (step S42). Here, it is assumed that the content server 30 decides to arrange the article contents C1 to C6 to be distributed in a vertical row such as the first, second, ... 7th from the top, as shown in FIG. ..

Further, when the advertisement servers 50a to 50c receive the advertisement request from the optimization server 20, they refer to a predetermined storage unit in the own device that stores various advertisement contents and distribute (display) to the user. The advertisement content of the distribution candidate which is a candidate is extracted (step S42). Here, as shown in FIG. 11, it is assumed that the advertisement server 50a extracts the advertisement content AD11, the advertisement server 50b extracts the advertisement content AD12, and the advertisement server 50c extracts the advertisement content AD13. In addition, for the sake of simplicity, an example in which each advertisement server extracts the advertisement content one by one is shown, but each advertisement server may extract a plurality of advertisement contents.

Further, what kind of advertisement content is extracted may follow the extraction logic of each of the advertisement servers 50a to 50c. For example, the advertisement server 50a and the advertisement server 50b extract the advertisement content based on the eCPM, the advertisement server 50b extracts the advertisement content based on the bid price, and so on, and so on, each advertisement server has its own extraction logic. Advertising content may be extracted with. On the other hand, the logic for extracting the advertising content may be unified.

Next, the content server 30 associates the data of the article content to be distributed with the arrangement order and transmits the data to the optimization server 20 (step S43). Further, each of the advertisement servers 50a to 50c also transmits the data of the advertisement content of the distribution candidate extracted by each of the advertisement servers 50a to 50c to the optimization server 20 (step S43). Then, the optimization server 20 transfers various data received from the content server 30 and the advertisement servers 50a to 50c to the user terminal 10 (step S44).

When the user terminal 10 receives the data from the optimization server 20, it calculates an index value indicating the degree of relevance between the advertisement content of the distribution candidate and the article content displayed around the arrangement position where the advertisement content of the distribution candidate is arranged. To do. Further, the user terminal 10 extracts the advertisement content to be displayed to be actually displayed to the user from the advertisement content of the distribution candidate based on the calculated index value (step S45).

The advertisement extraction process will be specifically described. For example, when seven contents are arranged in a vertical row, it is assumed that it is predetermined to insert the advertisement content at the arrangement position L10 (fourth) which is an intermediate position. As a result, the user terminal 10 calculates the similarity between the advertisement content of each distribution candidate and the article contents C2 to C5 from the placement position L10 to the upper and lower two articles, and uses the sum of the calculated similarity as an index value. calculate.

For example, the user terminal 10 calculates four similarities between the advertisement content AD11 and the article contents C2 to C5, and sums the calculated four similarities to the advertisement content AD11 and the vicinity of the arrangement position L10. The index value of the displayed article contents C2 to C5 is calculated. Then, the user terminal 10 calculates the advertisement evaluation value of the advertisement content AD11 by summing the calculated index value and the eCPM of the advertisement content AD11.

Further, the user terminal 10 calculates four similarities between the advertisement content AD12 and the article contents C2 to C5, and totals the calculated four similarities to obtain the advertisement content AD12 and the article contents C2 to C5. Calculate the index value of. Then, the user terminal 10 calculates the advertisement evaluation value of the advertisement content AD12 by summing the calculated index value and the eCPM of the advertisement content AD12. Further, the user terminal 10 calculates the advertisement evaluation value in the same manner for the advertisement content AD13.

Then, the user terminal compares each of the advertisement evaluation values calculated in this way, and extracts, for example, the one having the highest advertisement evaluation value as the advertisement content to be displayed. For example, assuming that the user terminal 10 extracts the advertisement content AD13 as a display target from the distribution candidate advertisement contents AD11 to 13, the web page W1a is generated from the extracted advertisement content AD13 and the article contents C1 to C6 to be distributed. Generate and display on the display screen.

In the advertisement extraction system 3 shown in FIG. 11, an example is shown in which the optimization server 20 mediates data transmission / reception between the user terminal 10 and the content server 30 and data transmission / reception between the user terminal 10 and the advertisement servers 50a to 50c. However, the advertisement extraction system 3 does not necessarily have the optimization server 20. In such a case, the user terminal 10 directly transmits the content request to the content server 30, and directly transmits the advertisement request to each of the advertisement servers 50a to 50c. The user terminal also receives data directly from each of the content server 30 and the advertisement servers 50a to 50c.

In this way, by performing the advertisement extraction process on the user terminal 10 side instead of the server side, for example, as shown in FIG. 11, even in a system in which advertisement server devices by a plurality of distributors coexist, the present embodiment It is possible to realize the advertisement extraction process related to.

[2. Terminal device configuration]
Next, the configuration of the user terminal 10 according to the third embodiment will be described with reference to FIG. FIG. 12 is a diagram showing a configuration example of the user device 10 according to the third embodiment. As shown in FIG. 12, the user device 10 includes a communication unit 11, an input unit 12, an output unit 13, and a control unit 14.

The communication unit 11 is realized by, for example, a NIC or the like. Then, the communication unit 11 is connected to the network by wire or wirelessly, and transmits / receives information between the optimization server 20, the content server 30, and the advertisement servers 50a to 50c.

The input unit 12 is an input device that receives various operations from the user. For example, the input unit 12 is realized by a keyboard, a mouse, operation keys, or the like. The output unit 13 is a display device for displaying various information. That is, the output unit 13 corresponds to the display screen of the user terminal 10. For example, the output unit 13 is realized by a liquid crystal display or the like. When a touch panel is adopted for the user terminal 10, the input unit 12 and the output unit 13 are integrated.

Returning to FIG. 12, the control unit 14 is realized by, for example, a CPU, an MPU, or the like executing various programs stored in the storage device inside the user device 10 using the RAM as a work area. Further, the control unit 14 is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 12, the control unit 14 includes a request unit 15, a calculation unit 16, an extraction unit 17, and a display control unit 18, and realizes or executes an information processing function or operation described below. To do. The internal configuration of the control unit 14 is not limited to the information shown in FIG. 14, and may be any other configuration as long as it is configured to perform information processing described later. Further, the connection relationship of each processing unit included in the control unit 14 is not limited to the connection relationship shown in FIG. 12, and may be another connection relationship.

The request unit 15 transmits a request for acquiring a predetermined content to a predetermined server. In addition, the request unit 15 accepts the content and the advertisement content of the candidate (delivery candidate) displayed in a list together with the content. In the example of FIG. 13, the request unit 15 transmits the request of the web page W1a to the optimization server 20. Further, the requesting unit 15 receives the article contents C1 to C6 listed as the web page W1a and the advertisement contents AD11 to AD13 of the distribution candidate from the optimization server 20.

The calculation unit 16 calculates an index value indicating the degree of relevance between the advertisement content of the distribution candidate and the article content displayed around the arrangement position where the advertisement content is arranged. For example, the calculation unit 16 calculates the similarity with the advertisement content of the distribution candidate for each content displayed around the placement position, and uses each calculated similarity with the content group displayed around the placement position. Calculate the index value with the advertisement content of the delivery candidate. Further, the calculation unit 16 calculates the advertisement evaluation value by summing the calculated index value and the evaluation value (for example, eCPM) of the advertisement content of the distribution candidate. That is, the calculation unit 16 is a processing unit corresponding to the calculation unit 133 of the advertising device 100.

The extraction unit 17 extracts from the advertisement content to be displayed to be displayed on the output unit 13 from the advertisement content to be distributed based on the index value calculated by the calculation unit 133. For example, the extraction unit 134 extracts the advertisement content of the distribution candidate having the highest advertisement evaluation value calculated by the calculation unit 133 based on the index value as a display target. That is, the calculation unit 16 is a processing unit corresponding to the extraction unit 134 of the advertising device 100.

The display control unit 18 controls the display of the content requested by the request unit 15 on the output unit 13. For example, the display control unit 18 creates a web page W1a from the article content and the advertisement content received by the request unit 15, and displays the created web page W1a on the output unit 13. Further, the display control unit 18 changes the display mode of the web page W1a according to the user operation, for example, when the user operation is performed on the web page W1a.

The processing of the advertisement extraction process by the control unit 14 described above may be realized by, for example, Javascript (registered trademark) or the like. Further, when the above-mentioned extraction process is performed by a predetermined application (for example, an application for displaying the web page W1), the control unit 14 functions as, for example, an application control unit that controls the predetermined application.

(Other embodiments)
The first to third embodiments described above may be implemented in various different forms other than the above-described embodiment. Therefore, other embodiments will be described below.

[1. List information]
In each of the above embodiments, the advertisement extraction process has been described using the web page W1 as an example of the list information in which a plurality of contents are arranged in a vertical row. However, the list information according to the present application may be a plurality of contents arranged in the vertical direction and the horizontal direction as in the web page W2a shown in FIG. Hereinafter, the index value calculation process for extracting the advertisement content arranged at the arrangement position L20 of the advertisement content included in the web page W2a will be described using the advertising device 100.

FIG. 13 is a diagram showing an example of an advertisement extraction process according to another embodiment. For example, the web page W2a shown in FIG. 13 conceptually shows a part of the web page W2. Here, it is assumed that the web page W2a is the initially displayed part of the web page W2.

In such a case, the request receiving unit 132 receives, for example, a list indicating the web page W2a from the content server 30. For example, the request receiving unit 132 receives a list in which the display position of the article content to be distributed and the text information are associated with each other. The display position of the article content to be distributed is indicated by, for example, the order and direction.

Assuming that the placement position L20 of the advertisement content, that is, the arrangement order is the i-th, the request reception unit 132 has "article content A1: i-third (left)" and "article content A2: i-3" in the example of FIG. We accept lists with notations such as "th (right)", "article content A3: i-2nd (right)", "article content A4: i-2nd (middle)", and so on.

In this way, when the list is received by the request reception unit 132, the calculation unit 133 determines, for example, the article contents from the arrangement position L20 to the upper and lower two article contents as the article contents around the arrangement position L20, and determines the article contents around the arrangement position L20. For each article content, the degree of similarity with the advertisement content I of the distribution candidate is calculated. That is, in the example of FIG. 13, the calculation unit 133 includes the distribution candidate advertisement content I, the i-2nd (left) article content A3, and the i-2nd (middle) article content A4, i-2nd. Article content A5, i-1st (left) article content A6, i-1st (right) article content A7, i + 1st (left) article content A8, i-1st (right) article content A9, The degree of similarity with i + 2nd (left) article content A10 and i + 2nd (right) article content A11 is calculated. Although the cosine similarity will be described here as an example of the similarity, it may be a category similarity.

FIG. 13 shows an example in which the calculation unit 133 calculates the cosine similarity cos _A3 as the similarity between the advertisement content I and the i-2nd (left) article content A3. Further, an example is shown in which the calculation unit 133 calculates the cosine similarity cos _A4 as the similarity between the advertisement content I and the i-2nd (middle) article content A4. The degree of similarity with other article contents is also as shown in FIG.

In addition, the calculation unit 133 adds a predetermined weight value to each calculated similarity. In pattern 1, the calculation unit 133 calculates the distance between the arrangement position L20 and the display position of each article content, and multiplies the weight value by the degree of similarity with the article content closer to the arrangement position L20. For example, the calculation unit 133 calculates the length of the straight line connecting the midpoint P20 of the arrangement position L20 and the midpoint of the display position of the article content as the distance between the arrangement position L20 and the display position of the article content.

The midpoint P20 of the placement position L20 corresponds to an intersection connecting the diagonal lines of the advertising area indicated by the placement position L20. Taking the article content A3 as an example, the midpoint of the display position of the article content A3 corresponds to the intersection connecting the diagonal lines of the content area indicated by the display position "i-2nd (left)". Information on such intersections (for example, coordinates) may be included in the list and transmitted from the content server 30, or the advertising device 100 may have information on each intersection in advance.

Then, the calculation unit 133 calculates the length D3 of the straight line connecting the midpoint P20 of the arrangement position L20 and the midpoint P3 of the display position of the article content A3. In this way, the calculation unit 133 calculates the length of the straight line connecting the midpoint P20 of the arrangement position L20 and the midpoint of the display position of each article content around the arrangement position L20. Since it can be determined that the article content having a shorter straight line length is closer to the arrangement position L20, the calculation unit 133 multiplies the article content having a shorter straight line length by a higher weight value. ..

In the example of FIG. 13, since the distance between the arrangement position L20 and the display position of the i-1st (left) advertisement content A6 and the i-1st (right) advertisement content A7 is the shortest, the article contents A6 and A7 Is closest to the placement position L20. Therefore, calculation unit 133, the similarity _{cos A7} of similarity _{cos A6} and advertising content I and article content A7 with advertising content I and article content A6, multiplied by the highest weight value r (0.9).

Further, in the example of FIG. 13, since the distance between the arrangement position L20 and the display position of the i + 1st (left) article content A8 and the i + 1th (right) article content A9 is the next shortest, the article contents A8 and A9 are It is the second closest position to the placement position L20. Therefore, calculation unit 133, the similarity _{cos A9} of similarity _{cos A8} and advertising content I and article content A9 with advertising content I and article content A8, higher weight values to the second ^r 2 (0.81) Multiply.

In this way, the calculation unit 133 adds up the similarities multiplied by the weight values to indicate the degree of relevance between the advertisement content I and the article content group from the placement position Lx to the upper and lower two articles. to calculate the S _I. Specifically, the calculation unit 133 can calculate the index value S _I by the following equation (8).

Index value _{^{S I = r 4 cos A3 +}} r 3 cos A4 + r 4 cos A5 + rcos A6 + rcos A7 + r 2 cos A8 + r 2 cos A9 + r 5 cos A10 + r 5 cos A11 ··· (8)

Then, calculating unit 133, based on the index value S _I calculated using Equation (8), calculates an advertisement evaluation value. For example, calculator 133 calculates the eCPM _I is an evaluation value of the advertising content I, the sum of the index value _{S I} calculated using Equation (8) as the advertisement evaluation value _{E I.} The extraction unit 134 compares the advertisement content each advertisement evaluation value E _I of each delivery candidate, extracts the advertisement content to be distributed.

Next, pattern 2 will be described. Pattern 2 is different from pattern 1 in the way weight values are assigned. Specifically, the calculation unit 133 multiplies a weight value higher by the degree of similarity with the article content closer to the placement position L20, by multiplying the weight value by the degree of similarity with the article content located above the placement position L20. ..

For example, the calculation unit 133 is the i-1st (left) article content A6 and the i-1st (right) article content A7, which are closest to the arrangement position L20 and located in the upper direction of the arrangement position L20, respectively. , Cos _A6 and cos _A7 , which are similarities to the advertising content I, are multiplied by the highest weight value r (0.9). Further, the calculation unit 133 determines that the i-2nd (middle) article content A4, which is next to the placement position L10 and is located above the placement position L10, and the advertisement content I have a degree of similarity cos _A4 . Multiply the highest weight value r ² (0.81).

In this way, the calculation unit 133 adds up the similarities multiplied by the weight values to indicate the degree of relevance between the advertisement content I and the article content groups from the placement position L10 to the upper and lower two articles content groups. to calculate the S _I. Specifically, the calculation unit 133 can calculate the index value S _I by the following equation (9).

Index value _{^{S I = r 3 cos A3 +}} r 3 cos A4 + r 3 cos A5 + rcos A6 + rcos A7 + r 4 cos A8 + r 4 cos A9 + r 5 cos A10 + r 5 cos A11 ··· (9)

Then, calculating unit 133, based on the index value S _I calculated using Equation (9), calculates the advertisement evaluation value. For example, calculator 133 calculates the eCPM _I is an evaluation value of the advertising content I, the sum of the index value _{S I} calculated using Equation (9) as the advertisement evaluation value _{E I.} The extraction unit 134 compares the advertisement content each advertisement evaluation value E _I of each delivery candidate, extracts the advertisement content to be distributed.

[2. Similarity calculation using image information]
In the above embodiment, the calculation unit 133 calculates the cosine similarity between the feature word extracted from the text of the advertisement content of the distribution candidate and the feature word extracted from the text of the article content displayed around the placement position. Indicated. However, not limited to this example, the calculation unit 133 includes a feature word extracted from the image data corresponding to the advertisement content of the distribution candidate and a feature word extracted from the image data corresponding to the article content displayed around the placement position. You may calculate the similarity of.

[3. Advertising device configuration]
In each of the above embodiments, an example is shown in which the advertisement device 100 or 200 performs the advertisement extraction process using the list received from the content server 30. However, the content server 20 and the advertising device 100 may be integrated into the advertising device 100. Further, the content server 20 and the advertising device 200 may be integrated into the advertising device 200.

[4. program〕
Further, the advertising devices 100 and 200 according to the above-described embodiments are realized by, for example, a computer 1000 having a configuration as shown in FIG. Hereinafter, the advertising device 100 will be described as an example. FIG. 11 is a hardware configuration diagram showing an example of a computer 1000 that realizes the functions of the advertising device 100. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a 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 part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, a program that depends on the hardware of the computer 1000, and the like.

The HDD 1400 stores a program executed by the CPU 1100, data used by such a program, and the like. The communication interface 1500 receives data from another device via the communication network 50 and sends it to the CPU 1100, and transmits the data generated by the CPU 1100 to the other device via the communication network 50.

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

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

For example, when the computer 1000 functions as the advertising device 100 according to the first embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 130 by executing the program loaded on the RAM 1200. Further, the data in the advertisement information storage unit 120 is stored in the HDD 1400. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be acquired from another device via the communication network 50.

Further, for example, when the computer 1000 functions as the advertising device 200 according to the second embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 430 by executing the program loaded on the RAM 1200.

[5. Others]
Of each of the processes described in the above embodiments, all or part of the processes described as being performed automatically may be performed manually, or all or part of the processes described as being performed manually. Some can be done automatically by a known method. In addition, the processing procedure, specific name, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified.

Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of the device is functionally or physically distributed / physically in arbitrary units according to various loads and usage conditions. It can be integrated and configured.

In addition, the above-described embodiments can be appropriately combined as long as the processing contents do not contradict each other.

Although some of the embodiments of the present application have been described in detail with reference to the drawings, these are examples, and various modifications are made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure column of the invention. It is possible to practice the present invention in other improved forms.

Further, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the determination unit can be read as a determination means or a determination circuit.

1 Advertisement extraction system 2 Advertisement extraction system 3 Advertisement extraction system 10 User terminal 14 Control unit 16 Calculation unit 17 Extraction unit 20 Optimization server 30 Content server 100 Advertising device 120 Advertisement information storage unit 130 Control unit 133 Calculation unit 134 Extraction unit 200 Advertisement Device 230 Control unit 236 Prediction unit

Claims (12)

It is the degree of similarity between the distribution candidate advertisement content displayed in a list together with the content and the content displayed around the arrangement position where the distribution candidate advertisement content is arranged, and indicates the display position of the distribution candidate advertisement content. The shorter the length of the line connecting the predetermined one point and the predetermined one point indicating the display position of the content displayed around the arrangement position where the advertisement content of the delivery candidate is arranged, the higher the weight value is weighted. An index value indicating the degree of relevance between the advertisement content of the delivery candidate and the content displayed around the placement position where the advertisement content of the delivery candidate is placed by calculating the calculated similarity and using the calculated similarity. And the calculation unit that calculates
An advertising device having an extraction unit that extracts advertisement content to be distributed from the advertisement content of the distribution candidate based on an index value calculated by the calculation unit. The calculation unit has a degree of similarity between the advertisement content of the distribution candidate and the content displayed around the arrangement position, and the content displayed around the arrangement position with a shorter line segment has a higher degree of similarity. The feature is that the similarity weighted by the weight value is calculated, and the calculated similarity is used to calculate an index value indicating the degree of relevance between the content displayed around the placement position and the advertisement content of the distribution candidate. The advertising device according to claim 1. The calculation unit calculates the similarity with the advertisement content of the distribution candidate for each content displayed around the arrangement position, and uses each calculated similarity to display the content group around the arrangement position. The advertising device according to claim 1 or 2, wherein an index value indicating the degree of relevance between the advertisement content and the advertisement content of the distribution candidate is calculated. Any of claims 1 to 3, wherein the calculation unit weights the content displayed around the arrangement position by a weight value having a higher degree of similarity to the content displayed above the arrangement position. The advertising device described in one. It also has a predictor that predicts the content that the user is interested in among the listed content and advertising content.
The calculation unit is described in any one of claims 1 to 4, wherein the calculation unit is weighted by a weight value having a higher degree of similarity to the content predicted to be of interest to the user by the prediction unit. Advertising equipment. The calculation unit is characterized in that the similarity between the information extracted from the text included in the advertisement content of the distribution candidate and the information extracted from the text included in the content displayed around the arrangement position is calculated. The advertising device according to any one of claims 1 to 5. The calculation unit is any one of claims 1 to 5, wherein the calculation unit calculates the degree of similarity between the category to which the advertisement content of the distribution candidate belongs and the category to which the content displayed around the arrangement position belongs. Advertising equipment described in. The calculation unit calculates an index value indicating the degree of relevance by summing the degree of similarity.
The extraction unit is characterized in that the advertisement content to be distributed is extracted from the advertisement content of the distribution candidate based on the sum of the index value calculated by the calculation unit and the evaluation value of the advertisement content of the distribution candidate. The advertising device according to any one of claims 1 to 7. A computer-executed ad extraction method
It is the degree of similarity between the distribution candidate advertisement content displayed in a list together with the content and the content displayed around the arrangement position where the distribution candidate advertisement content is arranged, and indicates the display position of the distribution candidate advertisement content. The shorter the length of the line connecting the predetermined one point and the predetermined one point indicating the display position of the content displayed around the arrangement position where the advertisement content of the delivery candidate is arranged, the higher the weight value is weighted. An index value indicating the degree of relevance between the advertisement content of the delivery candidate and the content displayed around the placement position where the advertisement content of the delivery candidate is placed by calculating the calculated similarity and using the calculated similarity. And the calculation process to calculate
An advertisement extraction method including an extraction step of extracting an advertisement content to be distributed from the advertisement content of the distribution candidate based on an index value calculated by the calculation step. It is the degree of similarity between the distribution candidate advertisement content displayed in a list together with the content and the content displayed around the arrangement position where the distribution candidate advertisement content is arranged, and indicates the display position of the distribution candidate advertisement content. The shorter the length of the line connecting the predetermined one point and the predetermined one point indicating the display position of the content displayed around the arrangement position where the advertisement content of the delivery candidate is arranged, the higher the weight value is weighted. An index value indicating the degree of relevance between the advertisement content of the delivery candidate and the content displayed around the placement position where the advertisement content of the delivery candidate is placed by calculating the calculated similarity and using the calculated similarity. And the calculation procedure to calculate
An advertisement extraction program characterized in that a computer executes an extraction procedure for extracting advertisement content to be distributed from the advertisement content of the distribution candidate based on an index value calculated by the calculation procedure. The reception department that accepts the content and the advertisement content of the distribution candidate displayed in a list together with the content,
The degree of similarity between the advertisement content of the distribution candidate received by the reception unit and the content displayed around the arrangement position where the advertisement content of the distribution candidate is arranged, and the display position of the advertisement content of the distribution candidate. The shorter the length of the line connecting the predetermined one point indicating the distribution candidate and the predetermined one point indicating the display position of the content displayed around the arrangement position where the advertisement content of the delivery candidate is arranged, the higher the weight value. The similarity weighted by is calculated, and the calculated similarity is used to indicate the degree of relevance between the advertisement content of the delivery candidate and the content displayed around the placement position where the advertisement content of the delivery candidate is placed. A calculation unit that calculates index values and
A terminal device including an extraction unit that extracts advertisement content to be displayed from the advertisement content of the distribution candidate based on an index value calculated by the calculation unit. The reception procedure for accepting the content and the advertisement content of the distribution candidate displayed in a list together with the content,
The degree of similarity between the advertisement content of the distribution candidate received by the reception procedure and the content displayed around the arrangement position where the advertisement content of the distribution candidate is arranged, and the display position of the advertisement content of the distribution candidate. The shorter the length of the line connecting the predetermined one point indicating the distribution candidate and the predetermined one point indicating the display position of the content displayed around the arrangement position where the advertisement content of the delivery candidate is arranged, the higher the weight value. The similarity weighted by is calculated, and the calculated similarity is used to indicate the degree of relevance between the advertisement content of the delivery candidate and the content displayed around the placement position where the advertisement content of the delivery candidate is placed. Calculation procedure to calculate the index value and
A terminal control program characterized in that a terminal device executes an extraction procedure for extracting advertisement content to be displayed from the advertisement content of the distribution candidate based on an index value calculated by the calculation procedure.

Images