JP6629268B2 - Advertising granting device, advertising granting method, and advertising granting program - Google Patents

Description

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

  2. Description of the Related Art In recent years, with the rapid development of the Internet, advertisements have been actively provided via the Internet. Advertisement is provided by displaying advertisement information such as an image or tagline displaying a company or product at a predetermined position on a web page, and transitioning to the advertiser's web page when the advertisement information is clicked. is there.

In recent years, techniques for devising a user so as to effectively recognize an advertisement have been proposed. For example, Patent Literature 1 discloses a terminal device capable of selecting an advertisement that matches a user's hobby and preference and providing the selected advertisement to the user.
In order to display an advertisement that attracts the user's interest, it is also effective to provide an advertisement (hereinafter, referred to as “recommended advertisement”) that is content-related to the article being viewed by the user. In this case, for example, a characteristic search word is specified from the article body, a search is performed on the advertisement server using the specified search word, and an advertisement related to the search word is determined.

JP 2015-22561 A

The provision of the recommended advertisement as described above requires a long time to search for the advertisement and the processing load on the advertisement server is large. Therefore, the number of articles to which the recommended advertisement is provided is limited.
On the other hand, because new articles are issued daily, the number of articles that can be advertised is enormous, and the ad may have a validity period, so once the recommended ad is Even if the article is given, it is necessary to give the recommended ad again when the validity period of the advertisement expires.

  As described above, since it is impossible to provide advertisements to all articles, conventionally, priorities are given according to predetermined conditions, and recommendation advertisements are given in descending order of priority. For low-priority articles, a default advertisement, for example, an advertisement with a large number of clicks, was given regardless of the content of the article.

  The present invention has been made in view of such circumstances, and an advertisement granting apparatus, an advertisement granting method, which can reduce a processing load and a processing time when providing an advertisement relating to an article, And an advertisement granting program.

In order to solve the above problems, the present invention employs the following solutions.
According to a first aspect of the present invention, a first storage unit storing classified advertisement information in which a classification of an article is associated with information of an advertisement related to each of the classifications, and analyzing contents of a target article to which the advertisement is to be given A classification specifying unit that specifies a classification of the target article; an advertisement determination unit that determines information of an advertisement to be provided to the target article by using the classified advertisement information and the classification of the target article; and an advertisement is provided. Second storage means for storing a plurality of articles which have not been stored, and recommendation advertisement determination means for providing, to some of the articles stored in the second storage means, recommendation advertisements related to the contents of the articles And an article providing means for creating the classified advertisement information from the recommended advertisement and the article to which the recommended advertisement has been added, and storing the classified advertisement information in the first storage means .

In a second aspect of the present invention, the content of a target article to which an advertisement is given is analyzed, and a classification specifying step of specifying the classification of the target article is associated with the classification of the article and the information of the advertisement related to each of the classifications. Using the classified classified advertisement information and the classification of the target article, an advertisement determining step of determining information of an advertisement to be provided to the target article, and a part of the articles among a plurality of articles to which no advertisement is provided. In response, a recommended advertisement determining step of providing a recommended advertisement related to the content of the article, a classified advertisement information creating step of creating the classified advertisement information from the recommended advertisement and the article to which the recommended advertisement is provided This is an advertisement providing method having the following.

According to a third aspect of the present invention, the content of a target article to which an advertisement is given is analyzed, and a classification specifying step of specifying a classification of the target article is associated with a classification of the article and information of an advertisement related to each of the classifications. An advertisement determining step of determining information of an advertisement to be provided to the target article using the classified advertisement information and the classification of the target article, and a part of the plurality of articles to which no advertisement is provided, A recommended advertisement determining step of providing a recommended advertisement related to the content of the article; a classified advertisement information creating step of creating the classified advertisement information from the recommended advertisement and the article to which the recommended advertisement is provided. Is an advertisement granting program for causing a computer to execute.

  ADVANTAGE OF THE INVENTION According to this invention, there exists an effect that the processing load at the time of giving the advertisement relevant to an article can be reduced and the processing time can be shortened.

It is a figure showing the whole advertising distribution system composition concerning one embodiment of the present invention. FIG. 2 is a diagram illustrating a hardware configuration of a media server, an advertiser server, and an advertisement distribution server according to an embodiment of the present invention. It is a functional block diagram showing an example of a function with which an advertisement giving device concerning one embodiment of the present invention is provided. It is a figure showing an example of classified advertising information with which an advertising grant device concerning one embodiment of the present invention is provided. It is the flowchart which showed the procedure of the advertisement provision process which the advertisement provision apparatus which concerns on one Embodiment of this invention performs.

Hereinafter, an advertisement providing apparatus, an advertisement providing method, and an advertisement providing program according to an embodiment of the present invention will be described with reference to the drawings.
FIG. 1 is a diagram showing an overall configuration of an advertisement distribution system having an advertisement providing device according to the present embodiment. As shown in FIG. 1, the advertisement distribution system 1 includes a media server 10, an advertiser (advertising agency) server 11, and an advertisement distribution server 12 as main components. In FIG. 1, the media server 10, the advertiser server 11, and the advertisement distribution server 12 are illustrated one by one, but the number is not limited to the illustrated embodiment, and may be appropriately increased according to the situation. It is possible. The media server 10, the advertiser server 11, and the advertisement distribution server 12 are communicably connected to each other via a network 15, and browse from various types of user terminals 13 similarly connected to the network 15 from the user terminal 13. The service according to the request (for example, distribution of articles and advertisements) is performed. An example of the network 15 is an Internet line, but other network lines may be used.

  The media server 10 is a server of mass media such as newspapers, magazines, radio broadcasts, and television broadcasts, and a server of a portal site. Various articles are uploaded daily. When the media server 10 receives an article browsing request from the user terminal 13 via the network 15, the media server 10 distributes the article to be browsed to the user terminal 13 via the network 15.

  The advertiser server 11 is a server that provides an advertisement for a product or service to the user terminal 13. For example, a server owned by an advertiser such as a corporation that provides a product, service, etc. to a consumer as an example, or an advertisement that performs a publicity advertisement on a product or service of the corporation in response to a request from the corporation. An example is a server owned by an agency. The advertiser server 11 stores various advertisements relating to products and services of the corporation and the like in an advertisement database.

  The user terminal 13 is a so-called information processing device such as a personal computer or a tablet terminal, and includes a communication unit for performing communication such as the Internet, an input unit for a user to input an input operation, and a display unit for displaying information. Having. For example, the user terminal 13 accesses the media server 10 via the network 15 and browses articles (contents) uploaded to the media server 10 using a web browser of the user terminal 13. In addition, the web browser of the user terminal 13 interprets the article acquired from the media server 10, for example, article content described in HTML (HyperText Markup Language) or the like, and transmits the article content from the media server 10 to the advertisement distribution server 12 according to the interpretation. Send the obtained article information and request an advertisement.

For example, when the advertisement distribution server 12 receives information of an article and a request for an advertisement from the user terminal 13, the advertisement provided to the article is read from the article advertisement information of an article advertisement database 32 (see FIG. 3) described later. The extracted advertisement is transmitted to the user terminal 13. Thereby, for example, an advertisement given to the article is displayed on the web page of the user terminal 13 together with the article requested to be browsed by the user.
The advertisement distribution server 12 has an advertisement providing device 20. The advertisement giving device 20 is a device that gives an advertisement related to the content of an article to which an advertisement has not been given (for example, a newly arrived article). The details of the advertisement providing device 20 will be described later. The information of the advertisement provided by the advertisement providing device 20 is stored in the article advertisement database (FIG. 3) provided in the advertisement providing device 20 in association with the information of the article, and is used for the advertisement distribution as described above.

Next, hardware configurations of the media server 10, the advertiser server 11, and the advertisement distribution server 12 according to the present embodiment will be described with reference to FIG. As shown in FIG. 2, the media server 10, the advertiser server 11, and the advertisement distribution server 12 are so-called computer systems. For example, the CPU 21 and a ROM (Read Only Memory) for storing a program executed by the CPU 21 and the like. 22, a RAM (Random Access Memory) 23 functioning as a work area when each program is executed, a hard disk drive (HDD) 24 as a large-capacity storage device, a communication interface 25 for connecting to a network, a keyboard and a mouse, etc. , And a display unit 27 such as a liquid crystal display device for displaying data. These components are connected via a bus 28.
The storage medium for storing the programs and the like executed by the CPU 21 is not limited to the ROM 22, but may be another recording medium including a magnetic disk, a magneto-optical disk, a semiconductor memory, and the like.
The ROM 22 stores various programs, and the CPU 21 reads out the programs from the ROM 22 to the RAM 23 and executes them to realize various functions.
The media server 10, the advertiser server 11, and the advertisement distribution server 12 do not necessarily need to have the display unit 27. The media server 10, the advertiser server 11, and the advertisement distribution server 12 may be connected to the input unit 26 via a network or the like, and may be configured to be operable remotely.

Next, the advertisement providing device 20 according to the present embodiment will be described in detail.
FIG. 3 is a functional block diagram illustrating an example of functions provided in the advertisement providing device 20. As shown in FIG. 3, the advertisement providing device 20 includes, for example, an article database ( second storage unit) 31, an article advertisement database 32, a classification database ( third storage unit) 33, and a classified advertisement database (first storage unit) 34. , An article selection unit 35, a recommended advertisement determination unit 36, a classified advertisement information creation unit 37, a classification identification unit 38, and an advertisement determination unit 39 as main components. The various processes described below realized by these units are realized by, for example, the CPU 21 reading out the advertisement giving program stored in the ROM 22 to the RAM 23 and executing it.

The article database 31 stores information on a plurality of articles to which no advertisement has been given. For example, the latest article published daily from each medium is registered and accumulated in the article database 31.
The article advertisement database 32 stores article advertisement information in which information of an article is associated with information of an advertisement provided to the article.

The classification database 33 stores classification information referred to when specifying the classification of an article. As an example of article classification, there is a method of specifying the classification from the appearance tendency of words appearing in articles. For example, by performing linguistic analysis such as morphological analysis or dependency analysis on a large number of articles, the articles are decomposed into words, and the appearance probabilities of the words (especially nouns) are statistically obtained to determine the tendency of the words to appear. obtain. As a result, a group of articles having similar appearance tendency of words is grasped as a cluster, and articles are classified by the cluster.
The classification database 33 stores, for example, classification information in which each classification (for convenience of description, for example, fashion, sports, politics, and the like) is associated with the appearance tendency of a word included in an article belonging to each classification. I have. Note that the method of classifying articles is not limited to this example, and a known method can be used as appropriate as to what index is used to classify articles.

  The classification may be hierarchized. For example, the classification of the first hierarchy is defined by a cluster of articles that will belong to a large framework such as “fashion”, “sports”, “politics”, and the like. , "Men's clothing", "women's clothing", "children's clothing", etc., may be defined by a cluster of articles that will belong to a more subdivided framework. It can be expected that the more subdivided or the more multi-layered the classification, the higher the relevance of the advertisement associated with the classification.

  The classified advertisement database 34 stores classified advertisement information in which the above-described article classification and information on recommended advertisements described later are associated with each other.

  The article selecting unit 35 selects a predetermined number of articles (hereinafter, referred to as “recommended articles”) to which a recommended advertisement is to be given, from a large number of articles stored in the article database 31 based on predetermined conditions. Here, the “predetermined condition” can be set as appropriate, and examples thereof include that the number of browsing times is equal to or less than a predetermined number of days after the article is issued and the number of browsing times is equal to or more than a predetermined number of times.

  The recommended advertisement determining unit 36 determines a recommended advertisement related to the contents of the article for the recommended article selected by the article selecting unit 35. Specifically, the recommended advertisement determining unit 36 analyzes the contents of the recommended article, specifies a search word for providing an advertisement, searches the advertiser server 11 using the specified search word, and searches the advertiser server 11 To obtain an advertisement related to the search word as a recommended advertisement. In addition, since a technique for searching for a recommended advertisement is a known technique, a known technique may be appropriately employed.

  Furthermore, the recommended advertisement determining unit 36 determines the information of the determined recommended advertisement (for example, identification information for specifying the recommended advertisement) and the information of the recommended article to which the recommended advertisement is assigned (for example, to specify the article). Is stored in the article advertisement database 32 in association with the identification number of the article, the content of the article, and a search word extracted from the article body.

The classified advertisement information creating unit 37 creates classified advertisement information in which the classification of the article and the information of the advertisement are associated with each other from the recommended article and the information of the recommended advertisement given to the recommended article, and stores the classified advertisement information in the classified advertisement database 34. .
Specifically, the classified advertisement information creating unit 37 analyzes the recommended articles and obtains the appearance tendency of words appearing in the recommended articles. Then, it compares the appearance tendency of the word of the recommended article with the appearance tendency of the word in each classification of the classification information stored in the classification database 33, and specifies the classification of the recommended article from the similarity of the appearance tendency of the word. For example, the classified advertisement information creating unit 37 searches the classification information having the highest similarity of the appearance tendency of words from the classification information, and specifies the classification of the recommended article.
Next, the classified advertisement information creating unit 37 creates classified advertisement information in which the information of the advertisement is associated with each article classification from the identified classification and the information of the recommended advertisement given to the recommended article. Is stored in the classified advertisement database 34.
Thereby, the classified advertisement database 34 stores, for example, classified advertisement information in which advertisement information is registered for each article classification, as shown in FIG.
An evaluation value is associated with the advertisement information in the classified advertisement information. The evaluation value is calculated, for example, using a predetermined calculation formula using at least one of a parameter related to the click probability of the advertisement and a parameter related to the advertisement profitability.

  The classification specifying unit 38 specifies the classification of an article that has not been selected as a recommended article by the article selecting unit 35 (hereinafter, referred to as a “normal article”) among many articles stored in the article database 31. The method of specifying the classification is the same as that of the above-described classified advertisement information creating unit 37, and thus the description is omitted.

The advertisement determining unit 39 gives an advertisement to a normal article. Specifically, the advertisement deciding unit 39 uses the classified advertisement information stored in the classified advertisement database 34 and the classification of each normal article specified by the classification specifying unit 38 to set an advertisement to be assigned to each normal article. To determine.
For example, for each ordinary article, the advertisement determining unit 39 searches the classified advertisement information for information on an advertisement that satisfies a preset condition based on the classification of each ordinary article, and determines an advertisement to be attached to each ordinary article.

Here, the “preset condition” is a matter that can be appropriately set by a designer, and is set so that an advertisement associated with a classification of a normal article and a classification having a similarity degree equal to or higher than a threshold is selected. Is preferred. By doing so, it is possible to easily give an advertisement related to the content of the normal article to the normal article.
Examples of the “predetermined conditions” include “advertising with the highest evaluation value among advertisements associated with the same classification as the normal article”, “ And the advertisement having the highest evaluation value among the associated advertisements. Further, when the classification has a hierarchical structure, it is necessary to set as a condition which hierarchical level matches. For example, when the second hierarchy is specified, if the classification of a normal article is “fashion / women's clothes”, it is associated with “fashion / women's clothes” from the classified advertisement information shown in FIG. “Advertisement D” having the highest evaluation value is selected from “Advertisements D, G, H”, and if the first hierarchy is specified, “Advertisement A” associated with “Fashion” , E, J, D, G, H ", the" advertisement A "having the highest evaluation value is selected. In addition, even if the classification is not the same as that of a regular article, if the classifications have a close relationship, search for an advertisement to be attached to the regular article, including the class having the close relationship. You may do it. Further, when there is no advertisement having the evaluation value equal to or more than the predetermined value in the same or similar classification, the advertisement having the highest evaluation value may be selected from all the classifications.

  When the advertisement information is added to the normal article in this manner, the advertisement information (for example, identification information for specifying the advertisement, etc.) and the information of the normal article to which the advertisement is added are determined. (Eg, an identification number for identifying an article, the content of the article, a search word extracted from the article body, etc.) and the article advertisement information stored in the article advertisement database 32.

  Next, an advertisement providing process performed by the advertisement providing apparatus 20 according to the present embodiment will be described mainly with reference to FIG. The advertisement providing process described below is a process that is repeatedly performed at a predetermined timing, for example, at a timing when the article database 31 is updated.

  First, the article selection unit 35 selects a predetermined number of articles (recommended articles) to which a recommended advertisement is given from articles stored in the article database 31 (SA1). Subsequently, a recommended advertisement is assigned to the recommended article by the recommended advertisement determining unit 36 (SA2), and the article advertisement information that associates the information of the recommended advertisement with the information of the recommended article to which the recommended advertisement has been added is included in the article advertisement. It is stored in the database 32 (SA3).

  Then, when the recommended advertisement is given to all the recommended articles ("YES" in SA4), the classification in which the classification of the article and the information of the advertisement are associated from the recommended article and the recommended advertisement given to the recommended article The advertisement information is created by the classified advertisement information creating unit 37 and stored in the classified advertisement database 34 (SA5). The classified advertisement information created in this way is associated with an evaluation value according to the number of user clicks and profitability of the recommended advertisement, and the evaluation value is updated each time these parameters are updated. It will be.

Next, the classification of the normal article (target article) not selected as the recommended article is specified by the classification specifying unit 38 (SA6). Subsequently, the advertisement deciding unit 39 assigns an advertisement to the regular article based on the classification of the regular article and the classified advertisement information stored in the classified advertisement database 34 (SA7), and assigns the advertisement to the information of the regular article. The article advertisement information associated with the advertisement information is stored in the article advertisement database 32 (SA8).
The provision of the advertisement to the normal article is continuously performed, for example, until advertisements are provided for all the normal articles stored in the article database 31 or until the article database 31 is updated (SA9). .

As described above, according to the advertisement providing apparatus, the advertisement providing method, and the advertisement providing program according to the present embodiment, the classified advertisement information in which the article classification and the advertisement information are associated with each other, The advertisement to be attached to the normal article is determined using the classification of the normal article (target article). This makes it possible to significantly reduce the time required for providing advertisements for regular articles, and to efficiently provide advertisements for more articles.
Further, by creating classified advertisement information from information of a recommended article and information of a recommended advertisement given to the recommended article, it is possible to associate only information of an advertisement related to the article with each classification. Thus, by using the classified advertisement information, it is possible to efficiently provide an advertisement having relatively high relevance to the content of the article.

As described above, the present invention has been described using the above embodiment, but the technical scope of the present invention is not limited to the scope described in the above embodiment. Various changes or improvements can be made to the above-described embodiment without departing from the spirit of the invention, and embodiments with such changes or improvements are also included in the technical scope of the present invention. Further, the above embodiments may be appropriately combined.
In the above-described embodiment, the procedure of the process in the advertisement providing apparatus has been described. However, these procedures are merely examples, and unnecessary processing steps may be deleted or new processing steps may be performed without departing from the gist of the present invention. May be added or the processing steps may be interchanged.
For example, in the flowchart shown in FIG. 5, the case where the classified advertisement information is created after the recommendation advertisement is given to all the recommended articles has been described, but instead, for example, for one recommended article, Classified advertisement information may be created each time a recommended advertisement is given, or classified advertisement information may be created every time a recommended advertisement is given to a predetermined number of recommended articles. As described above, the creation timing of the classified advertisement information can be determined as appropriate.

1 Advertisement Distribution System 10 Media Server 11 Advertiser Server 12 Advertisement Distribution Server 13 User Terminal 15 Network 20 Advertisement Apparatus 31 Article Database ( Second Storage Means)
32 article advertisement database 33 classification database ( third storage means)
34 Classified advertisement database (first storage means)
35 article selection unit 36 recommended advertisement determination unit 37 classification advertisement information creation unit 38 classification specification unit 39 advertisement determination unit

Claims (8)

First storage means for storing classified advertisement information in which a classification of an article is associated with information of an advertisement related to each of the classifications;
Analyzing the content of the target article to which the advertisement is given, classification specifying means for specifying the classification of the target article,
Using the classified advertisement information and the classification of the target article, an advertisement determining unit that determines information of an advertisement to be provided to the target article,
A second storage unit in which a plurality of articles to which no advertisement is given are stored;
Recommended advertisement determining means for providing a recommended advertisement related to the content of the article to some of the articles stored in the second storage means,
An advertisement providing apparatus comprising: a classified advertisement information creating unit that creates the classified advertisement information from the recommended advertisement and the article to which the recommended advertisement has been assigned, and stores the created classified advertisement information in the first storage unit . Article selection means for selecting, from a plurality of articles stored in the second storage means, a recommendation article to which a recommendation advertisement related to the content of the article is given based on a predetermined condition,
The recommendation advertisement determination means, the recommendation article is provided with the recommendation advertisement,
The category specifying means, among the plurality of articles stored in said second storage means, the articles which have not been selected as the recommendation article as the target article, in claim 1 to identify the classification of the subject article The advertisement providing device according to the above. The ad determination means, information satisfies advertisement which is preset based on the classification of the target articles retrieved from the classified ads information, claim 1 to determine the advertisement information to be applied to the target article or The advertisement providing device according to claim 2 . The advertisement information in the classified advertisement information is associated with the evaluation value of the advertisement,
The ad determination means, advertisement providing device according to any one of claims 1 to 3 for determining the advertisements to be applied to the target article using the evaluation value of the advertisement. The advertisement providing apparatus according to claim 4 , wherein the evaluation value of the advertisement is determined using at least one of a parameter related to a click rate of a user and a parameter related to advertisement profitability. A third storage unit for storing classification information in which the classification of the article and the information on the tendency of appearance of words are associated with each other;
The category specifying means, from said similarity to the emergence tendency of a word and occurrence tendency of a word appearing in the target article is registered in the classification information, claim from claim 1 to identify the classification of the subject article 5 The advertisement providing device according to any one of the above. Analyzing the content of the target article to which the advertisement is given, a classification specifying step of specifying the classification of the target article,
An advertisement determining step of determining information of an advertisement to be provided to the target article by using the classified advertisement information in which the classification of the article and the information of the advertisement related to each of the classifications are associated and the classification of the target article,
Among a plurality of articles to which no advertisement is given, for some of the articles, a recommended advertisement determining step of providing a recommended advertisement related to the content of the article,
A classified advertisement information creating step of creating the classified advertisement information from the recommended advertisement and the article to which the recommended advertisement has been assigned . Analyzing the content of the target article to which the advertisement is given, a classification specifying step of specifying the classification of the target article,
An advertisement determining step of determining information of an advertisement to be provided to the target article by using the classified advertisement information in which the classification of the article and the information of the advertisement related to each of the classifications are associated and the classification of the target article;
Among a plurality of articles to which no advertisement is given, a recommendation advertisement determining step of giving a recommendation advertisement related to the content of the article to some of the articles,
An advertisement assignment program for causing a computer to execute a classified advertisement information creating step of creating the classified advertisement information from the recommended advertisement and the article to which the recommended advertisement has been assigned .

Images