JP2023063164A - Advertisement providing target setting information management apparatus and method - Google Patents

Abstract

To provide an advertisement providing target setting information management apparatus, a method therefor, and a program therefor which, without setting fine adjustment of meta information for an advertisement by an advertiser, through the advertiser's selection of a sympathy theme which the advertiser wants to post, specifies and posts content suitable for the theme.SOLUTION: A method of an advertisement providing target setting information management server 100 has a step of allocating a sympathy theme to content based on meta information on the content, a step of acquiring advertisement providing target setting information by selecting content matched with the sympathy theme set by an advertiser with a content selection unit 122, and a step of providing an advertisement linked with the content based on the advertisement providing target setting information.SELECTED DRAWING: Figure 5

Description

The present invention relates to an apparatus and method for managing setting information of an advertisement target to which an advertisement is to be provided, and in particular, enables selection of an advertisement target by using highly abstract words and phrases that match the advertisement intent of the advertiser. It is.

In order to improve the cost effectiveness of Internet advertising, content-linked advertising has been adopted. Content-linked advertising, which is also called display advertising, is a network advertising method in which displayed advertisements are determined according to the content of a website. This advertising method has the feature of being able to approach browsing users who are interested in content as a latent layer. FIG. 1 shows an example of a content-linked advertisement for an article on a website. Ads typically appear on the edges and corners of the site. This content-linked advertisement is described, for example, in Japanese Patent Publication No. 2006-500698.

In this content-linked advertisement, in order to improve the cost effectiveness of Internet advertising, the categories of content (articles, blogs, introduction information, videos, etc.) are limited to those that match the impression (image) of the advertisement. , the items and products described in the content, and the topic (theme) of the content are limited to those that match the impression of the advertisement.

For example, the relationship between the content of the advertisement publication destination and the advertisement to be published is associated with each meta information, and this association is determined and adjusted by the advertiser's setting.

[1. Addition of meta information to content]
Assignment and management of meta information to contents are as follows. That is, each content is managed by assigning attributes and tags according to the details of the content. Meta information is, for example, category information and feature words (hereinafter also referred to as meta words). The category information means the topic category (genre) of the content. For example, there are classification methods such as fashion, beauty, gourmet, and travel. Also, if the content has seasonal characteristics, it can be "spring/summer/autumn/winter", target person image "20s/30s... male/female/pregnant woman/mother...", location "Hokkaido , Okinawa, North America, Europe...".

Also, a word (characteristic word) indicating the feature of the content is extracted from the title or text of the content and managed as meta information (meta assignment). It is also common practice to post a part of this meta information as tag information as information related to web content, and to browse the content information to which the same tag information is assigned by clicking. Characteristic words include, for example, summer, coordination, white T-shirt, casual, sandals, everyday use, fashionable, simple, cleanliness, and so on.

[2. Addition of meta information to target advertisements]
Meta information is added to the target advertisement as well. In other words, the above-described meta information is added to the target of the advertisement from the description or the like. At this time, in addition to the information extracted from the target advertisement, the advertiser intentionally adds words that express the impression or characteristics of the target advertisement as meta information, or conditions for the article to be advertised, such as genre, season, etc. It is also possible to specify settings, target persons, weighting conditions (words to be included, words not to be included), and the like.

[3. Relationship between advertising target and content]
Which content is to be advertised is determined based on the relationship between the advertisement target and the content. In other words, the meta information attached to these target advertisements and the meta information attached to each content are compared, and based on the number of matching words and the number of highly similar words, the relationship between the advertisement and the article is determined. A matching score is calculated, and ads are displayed on content with a high score.

As described above, the advertiser can place the advertisement in the content matching the target advertisement by the steps 1 to 3.

By the way, [2. Meta information addition to target advertisement], by adjusting and setting the meta information for the target advertisement according to the request of the advertiser, it is possible to finely adjust the designation of the content in which the target advertisement is posted.

However, in this method, for example, when an advertiser wants to display an advertisement in content related to "unwavering values" so as to give the user the impression that the target advertisement is "unwavering values", [3. Relation between advertisement target and content], it is necessary to add or delete meta information attached to the target advertisement so as to match the relevant content. Addition of meta information to target advertisement] and [3. Relation between advertisement target and content] is required to be repeatedly adjusted.

In addition, since this method adjusts the meta information attached to the target advertisement, it is possible to intentionally change the impression of the target advertisement significantly, or to use content related to a category that is completely different from the category (genre) of the target advertisement. It is difficult to adjust so that it is associated with

Japanese Unexamined Patent Application Publication No. 2010-009307 is a prior art document related to this invention. In this prior art document, a feature word related to a "product category" is acquired in advance from a learning text, and in order to select web content on which an advertisement is to be placed based on the product category, web content to be provided with advertisement is compared with a characteristic word related to the product category, and web contents with a high degree of matching are determined as advertisement placement destinations.

It should be noted that the present invention should not be understood in a limited manner due to the problems described above, and the content thereof is defined in the claims and will be described in detail below using examples.

Japanese Patent Publication No. 2006-500698 JP 2010-009307 A

It is preferable to easily select an advertisement providing target that matches the intention of the advertiser.

Here, before describing the invention in detail, the description of the scope of claims will be supplementarily described. It should be noted that although the reference numerals in the drawings are attached together for easy understanding, it should be noted that this does not mean that the configurations are limited to the embodiments.

According to one aspect of the present invention, in order to achieve the above-described object, an advertisement target setting information management device (100) includes: a metaword for advertisement target candidate content for associating one or more metawords with an advertisement target candidate content; Meta word association data storage means (104A) for candidate contents for advertisement provision target that holds association data; and each of a plurality of advertisement feature description words and phrases prepared in advance for independently describing an advertisement feature, each of which has the advertisement feature description. an advertising characterizing phrase group association data holding means (108) for holding advertising characterizing phrase group association data for associating characterizing phrase groups prepared in advance to characterize each of the phrases; The metaword association data for the candidate content for advertisement provision held in the metaword association data holding means for the candidate content for advertisement provision and the advertising feature held in the characterizing phrase group association data for advertisement feature description phrase means for associating one or a plurality of the advertisement characteristic description phrases with each of at least a part of the candidate contents for advertisement provision based on the characterization phrase group association data for the content to be provided advertisement (110) ); and; obtaining one or more of the advertisement characteristic description phrases corresponding to the specified advertisement, and selecting the advertisement providing target content based on the association with the obtained advertisement characteristic description phrase, and advertising Advertisement provision target content selection information generating means (122) for generating provision target content selection information is provided.

According to this configuration, it is possible to easily generate the advertisement presentation target content selection information for mapping the advertisement and the advertisement presentation target content through the medium of the advertisement feature description phrase describing the feature of the advertisement. An advertiser can set an advertisement providing target that matches the advertisement intention based on the advertisement characteristic description phrase, and can easily respond by changing the advertisement characteristic description phrase when changing or adjusting the advertisement intention. .

The advertising feature descriptor is typically the theme of the advertisement, sometimes referred to as the "empathy theme" in the examples below. For example, it is preferable to prepare 100 to 200 “empathy themes”, but the present invention is not limited to this. "Sympathy themes" can be specific themes such as "recommended for summer," "enjoying a stay-at-home life," or "comfortable life on rainy days," or "living in your own way," or "extraordinary experiences." , ``consistent values'', and ``heartwarming happiness''. An advertisement concept (concept) or an advertisement motif (material) may be used instead of or in addition to the advertisement theme.

This invention is for selecting a content destination for advertising when an "advertiser" advertises a product or corporate image in a form associated with content. By selecting an advertisement feature description phrase (“empathy theme”) that matches the “impression” of the advertisement target, the owner can more easily select the content of the advertisement destination. As an application example of this advertising technique, for example, content-linked advertisement can be considered, but it is not limited to this.

Also, in this configuration, the candidate content for which advertisements are provided may be content displayed on the web, but is not limited to this.

Also, the advertising characterizing phrases may consist of words, phrases or sentences.

Also, the metaword may be composed of words or phrases and given to the object. Metawords may be automatically extracted and assigned from text or the like associated with an object.

Also, the characterizing phrases that are members of the characterizing phrase group may consist of words, phrases or sentences. This group of characterizing phrases may also be automatically extracted from text or the like related to the advertising theme. The designer may separately prepare or adjust. The characterizing phrases in the characterizing phrase group may be equivalent to or alternative to the metawords. The identity of the characterizing words and metawords may be determined by appropriate name identification processing or the like.

Further, the metaword association data for candidate content for advertisement provision target may specify one or more metawords associated with each of the candidate content for advertisement provision and the degree of importance (score) of each.

Further, the advertising characterizing phrase group association data may specify, for each of the advertising characterizing phrases, phrases in the associated characterizing phrase group and their respective importance.

Further, the apparatus may further include means for generating the metaword association data for the candidate content for the advertisement, based on the information regarding each of the candidate contents for the advertisement.

Further, the advertisement provision target setting information management device further includes: means for inputting advertisement target information; and advertisement characteristic description phrase determination means for determining an advertisement characteristic description phrase for the advertisement based on the inputted advertisement target information. Good to have more.

Further, the advertising characteristic descriptive phrase determination means extracts one or more characteristic phrases from the advertisement target information, and the characteristic phrases are held in the advertisement characteristic phrase phrase group association data holding means. Corresponding advertising theme descriptors may be determined based on the advertising feature descriptor phrase characterization phrase group association data.

Further, according to another aspect of the present invention, in the advertisement provision target setting information management device (100): one selected from a plurality of advertisement characteristic description phrases prepared in advance for independently describing the characteristics of each advertisement; or advertising feature description phrase association data storage means for advertisement target candidate content (104B) that holds advertising feature description phrase association data for advertisement target candidate content that associates a plurality of advertisement feature description phrases with advertisement target candidate content; Advertisement information input means (112) for inputting target information; Advertisement feature description phrase determination means (118) for determining an advertisement feature description phrase for the advertisement based on the input advertisement target information; On the other hand, the advertisement feature description phrase determined by the advertisement feature description phrase determination means and the advertisement feature description for the candidate content for advertisement provision held in the advertisement feature description phrase association data holding means for the candidate content for advertisement provision. Advertisement target content selection information generation means (122) for selecting the advertisement target content based on the word/phrase association data and generating advertisement target content selection information.

With this configuration as well, it is possible to easily generate advertisement target content selection information for mapping an advertisement and an advertisement target content through an advertisement feature description phrase describing the feature of the advertisement. An advertiser can set an advertisement providing target that matches the advertisement intention based on the advertisement characteristic description phrase, and can easily respond by changing the advertisement characteristic description phrase when changing or adjusting the advertisement intention. .

Further, in this configuration, the advertisement target setting information management device further includes a selection means for the user to select an advertisement characteristic description phrase; and the advertisement target information and the advertisement characteristic description phrase selected by the selection means. and matching degree output means for outputting a degree of matching based on.

Further, in this configuration, the advertisement target setting information management device further includes a selection means for the user to select an advertisement characteristic description phrase; and the advertisement target information and the advertisement characteristic description phrase selected by the selection means. and a divergence output means for outputting the divergence based on.

According to another aspect of the present invention, the content-linked advertising system includes: a user device; a server device for supplying advertisement target setting information to the user based on a request from the user device; a server for supplying content to the user device based on a request from the user device; In addition to the contents supplied from the server, the list of advertisements is displayed based on the advertisement target content selection information supplied from the advertisement target setting information supply server device.

According to this configuration, it is possible to determine the advertisement providing destination based on the advertisement feature description phrase, so that it becomes easy to operate the content-linked advertising system that meets the intention of the advertiser.

The present invention can be implemented not only as an apparatus or system, but also as a method. Moreover, of course, a part of such an invention can be configured as software. Naturally, a software product (computer program) used to cause a computer to execute such software is also included in the technical scope of the present invention.

The above aspects and other aspects of the present invention are described in the claims and will be described in detail below using examples and the like.

According to this invention, it is possible to easily select an advertisement providing target that matches the intention of the advertiser.

It is a figure explaining the example of the conventional content-linked advertisement. It is a figure explaining the environment in which the advertisement provision target setting information management server of the Example of this invention is used. FIG. 4 is a diagram illustrating a schematic operation example in an environment in which the advertisement provision target setting information management server of the embodiment of this invention is used; It is a figure explaining the computer resource of the advertisement provision target setting information management server of the Example of this invention. It is a functional block diagram explaining the functional structure of the advertisement provision target setting information management of the Example of this invention. FIG. 5 is a flow diagram illustrating an operation example of advertisement provision target setting information management according to the embodiment of this invention; 4 is an example of empathy theme and component information for use in embodiments of the present invention; FIG. 4 is a diagram illustrating mapping of empathy themes and content in an embodiment of the present invention; FIG. 4 is a diagram illustrating empathetic theme-mediated mapping between advertisements and content in an embodiment of the present invention; It is a figure explaining the example which acquires a metaword from a text in the Example of this invention. 11 is a diagram illustrating an example of metaword extraction in the example of FIG. 10; FIG. FIG. 11 is a diagram illustrating an example of calculation of importance scores of metawords in the example of FIG. 10; FIG. 4 is a diagram illustrating an example of adding meta information to content and advertisements in the embodiment of this invention; It is a figure explaining the example of the empathy theme used by the Example of this invention. It is a figure explaining the example which gives. FIG. 4 is a diagram illustrating the relationship between empathy themes and related phrases (sub-themes) in the embodiment of this invention; It is a figure explaining the example of the meta word used by the Example of this invention. It is a figure explaining the example of the sympathy theme associated with advertisement information and advertisement which are used in the Example of this invention. 18 is a diagram illustrating examples of metawords and score values extracted from the advertisement information of FIG. 17; FIG. FIG. 4 is a diagram illustrating examples of empathy themes, related phrases (subthemes), and metawords in the embodiment of the present invention; FIG. 4 is a diagram illustrating a notation example of meta weights of empathy themes (related phrases) in the embodiment of the present invention; It is a figure explaining the calculation example of matching of an advertisement and a sympathetic theme (related phrase) in the Example of this invention. It is a functional block diagram explaining the functional structure of the modification of the Example of this invention.

An advertisement provision target setting information management server and a content-linked advertisement system using the same according to an embodiment of the present invention will be described below.

As described above, FIG. 1 shows a display screen of a content-linked advertisement. For example, article title A1 and article body A2 constitute the content being viewed. Advertisements 1-8 are listed in the lower area A3 in relation to this content, and a desired advertisement can be clicked to move to the corresponding page.

In this embodiment, features such as topical themes with which a content browsing user can sympathize with and are interested in are defined as a plurality of "sympathetic themes". In a specific example, this "empathy theme" (hereinafter, the square brackets are omitted as appropriate) is prepared and defined in advance by the system operator. Specifically, 100 to 200 empathy themes are prepared in advance. A relatable theme consists of words and phrases that describe the characteristics of an advertisement that can be used to extract relevant advertisements. Phrases that describe the characteristics of advertisements (sympathy themes) are, for example, the themes of advertisements, such as "unwavering values", "wanting to continue to deliver happiness", "positiveness to continue to take on challenges", "be yourself", and "enchanted". cuteness to do" and the like (explained later with an example in FIG. 14, etc.).

For example, as an example, consider associating content (articles) and advertisements with a common theme of "unwavering values." As shown in FIG. 7, the sympathetic theme itself of "unwavering values" is associated with related words (also referred to as constituent elements, element words, and metawords) that make up the sympathetic theme, and each element word has a related word. A weighted score value according to gender is also defined. Element words can be words, phrases, and sentences. A group of element words associated with one sympathetic theme collectively characterize the sympathetic theme. In addition to or instead of the sympathetic theme, one or more "related phrases" (also called "subthemes") may be provided. Sympathetic themes represent related phrases. By providing a plurality of related phrases for one sympathetic theme, it is possible to perform multifaceted characterization. In the example below, "Related Phrases" have meta-information (meta-words and weight values), but empathy themes themselves may also contain meta-information. That is, when the sympathetic theme does not contain meta-information, the related phrase as a whole represents the characteristics of the object of description, and the words of the sympathetic theme represent the overall title of the related phrase (FIG. 19). If the sympathetic theme also contains meta-information, the sympathetic theme and related phrases as a whole represent the characteristics of the object of description, and the overall title of the sympathetic theme and related phrases are represented by the words of the sympathetic theme.

FIG. 2 illustrates an environment in which the advertisement target setting information management server 100 of the embodiment of this invention is used. In this figure, the advertisement target setting information management server 100 is connected to a communication network 400. ing. A web server 200 and a user terminal 300 are connected to this communication network 400 . Although only one web server 200 and one user terminal 300 are shown, there are usually more than one. Various content providing servers may be employed in place of the web server 200 . The user can use the user terminal 300 to obtain content information from the web server 200 and view it (areas A1 and A2 in FIG. 1). Further, the user terminal 300 acquires the advertisement target setting information from the advertisement target setting information management server 100 when browsing the content, and enables display of the advertisement (area A3 in FIG. 1).

FIG. 3 schematically shows the implementation configuration of the advertisement target setting information management server 100. The computer 1000 implemented includes a CPU 1001, a main memory 1002, an input/output interface (input/output bus) 1003, and an external ruler. 1004 and the like. By installing the application 1005 in the computer 1000, the advertisement provision target setting information management server 100 is constructed. It should be noted that it may simply be called the setting information management server 100 .

Although FIG. 4 shows a usage example of the advertisement provision target setting information management server 100, it is not limited to this. In FIG. 4, when a browsing request is sent from the user terminal 300 to the web server (H1), a content document is returned from the web server 200 (H2). Display is performed in areas A1, A2, and the like. When the user terminal 300 makes a browsing request to the web server 200 (H1), an advertisement information request is sent to the setting information management server 100 (H3). Advertisement provision target setting information for the content document is extracted, the advertisement provision target is determined, and advertisement display information such as its URL and thumbnail is returned to the user terminal 300 (X4). User terminal 300 displays an advertisement in area A3 (FIG. 1) based on the advertisement display information. When the user clicks on the advertisement, the advertisement document is sent to the user terminal 300 accordingly, and the click action is returned to the setting information management server 100 or the like for management.

FIG. 5 shows a functional configuration example of the advertisement target setting information management server 100 of this embodiment. In this figure, the advertisement target setting information management server 100 includes a content meta information extraction unit 102, a content management Information storage unit 104, sympathy theme component element information extraction unit 106, sympathy theme component element information storage unit 108, content sympathy theme determination unit 110, advertisement information input unit 112, advertisement feature word extraction unit 114, setting information adjustment unit 116, an advertisement sympathetic theme determination unit 118, an advertisement target setting information storage unit 120, a content selection unit 122, an advertisement target setting information transmission request receiving unit 124, and the like. The content management information storage unit 104 has a meta information storage unit 104A for storing content meta information and a sympathy theme storage unit 104B for storing content sympathy themes. can be managed. Meta information and empathy themes may be managed integrally for each content using the same table or the like.

The advertisement provision target setting information management server 100 shown in FIG. 5 will be described with reference to FIG. 6 and the like. FIG. 6 illustrates an operation example of advertisement provision target setting information management according to the embodiment of the present invention.

5 and 6, the content meta-information extracting unit 102 acquires information about the contents of the content (X01), extracts feature words (X02), adds meta information to the content (X03), is stored in the meta information storage section 104A of the management information storage section 104 for contents. An example of extraction of feature words will be described later. Meta information is typically feature words (metawords) and weightings, word categories (genres), and the like.

The component element information of each empathy theme is stored in the database or storage of the empathy theme component information storage unit 108 . The constituent element information of each empathy theme is compared with the meta information of each content, and a theme with a high matching score is regarded as an empathy theme highly relevant to the content, and the content management information storage unit 104 ( (X06).

The matching between contents (and advertisements) for this empathetic theme may be performed by comparing the meta information of the contents with the component information of the empathetic theme, but is not limited to this. Matching may check for agreement or similarity between each piece of content meta information and each piece of empathic theme component information, or may be based on similarity of semantic space word vectors, or a combination of both. It can be a method to

FIG. 8 shows the relationship between empathy themes and related content. In this example, "sympathetic theme 1" is associated with "content 1", "sympathetic theme 2" is associated with "content 2", and "sympathetic theme 1" and "sympathetic theme 2" are associated with "content 3". indicates that Content may have multiple empathy themes associated with it, and some content may have no empathy themes associated with it.

This matching process is executed as a backend process once a day, for example, when adding or modifying empathy themes or adding content. Information on empathy themes with a high degree of matching with each content is managed as attribute information for each content.

In the flow shown in FIG. 6, X01 to X06 indicate processing for associating empathy themes with content. First, the content meta-information extraction unit 102 inputs information about the content of the content (X01), extracts words representing the content from the content (X02), selects characteristic words from the extracted words, Meta information is added to the content (X03), and the result is stored in a storage such as a database (X04).

On the other hand, the sympathetic theme constituent element information extraction unit 106 collects texts and the like related to each sympathetic theme (or its related phrases), and extracts constituent element information (feature word information) therefrom. This can be extracted in the same manner as the technique described later in the extraction of feature words for content. There are, for example, 100 to 200 sympathetic themes as described above, and the constituent element information (characteristic word information) may be prepared manually. The sympathetic theme component information is stored and managed in the sympathetic theme component information storage unit 108 . The content empathy theme determining unit 110 compares the empathy theme component information in the empathy theme component information storage unit 108 with the content meta information in the content management information storage unit 104 (meta information storage unit 104A) to determine each A sympathetic theme for the content is determined (X05). As noted above, some content may not be assigned a relatable theme, and some content may be assigned multiple relatable themes. The empathy theme for each content is stored and managed in the empathy theme storage unit 104B of the content management information storage unit 104 (X06). An example of mapping between contents and empathy themes is as shown in FIG. 9, for example. Although the meta information storage unit 104A and the sympathetic theme storage unit 104B are shown as separate entities, they may be collectively managed in one table.

The advertisement information input unit 112 is for inputting information regarding the content of advertisement (FIG. 6, X11). An example of the information on the content of the advertisement and its processing will be described later with reference to FIGS. 17 and 21 and the like.

X11 to X17 in the operation example of FIG. 6 show the flow of associating the advertisement target with the content related to the sympathetic theme. The advertisement target here includes not only a specific "product" but also a product series such as a "brand" and a "company name", but is not limited to this.

Advertisement information input unit 112 inputs explanatory text, incidental information, and the like registered by the advertiser for the advertisement target (X11). The advertisement characteristic word extracting unit 113 extracts characteristic words related to the advertisement target from the explanatory text, supplementary information, and the like (X12).

The advertiser uses the setting information adjustment unit 118 to delete inappropriate information from the information automatically extracted in step X12, or intentionally adds words representing impressions and characteristics of the advertised target. You can It is also possible to specify conditions for the content in which the advertisement is to be placed, such as genre, season setting, target person, weighting conditions (words to be included, words not to be included), and the like. In this way, the information edited by the advertiser is set as the meta information of the advertisement target (X13), and then the setting content is saved in the database or storage of the advertisement provision target setting information storage unit 120 (X15). .

The advertisement sympathy theme determination unit 114 can obtain a sympathy theme candidate list related to the advertisement target meta information set in step X13. For example, the degree of matching may be calculated by matching the meta information (particular feature word) of the advertisement target with the feature word of each empathy theme, and based on this, the empathy theme candidate list may be obtained. By referring to the content information management database of the content management information storage unit 104 (sympathetic theme storage unit 104B), it is possible to confirm individual contents related to the sympathy theme included in each of the sympathy theme candidate lists. In addition, statistical information such as the total number of related contents and genre ratio can be confirmed (X14).

In this process, in addition to automatically obtaining a candidate list of sympathetic themes, sympathetic themes registered in the system may be searched, or designated and selected from a list. When setting empathy themes manually in this way, it is assumed that there will be a mismatch with the actual characteristics of the advertisement target, such as the theme, or with the meta information obtained from the advertisement information. etc.) may be provided at the same time. This will be detailed later.

Based on the information, the advertiser registers a sympathetic theme associated with the advertisement target in the advertisement provision target setting information storage unit 120 (X15).

The content selection unit 116 searches the content information management database of the content management information storage unit 104 (sympathy theme storage unit 104B) for content to which the same sympathy theme is assigned as an attribute for the sympathy theme associated with the advertising target. Identify by doing. At this time, the conditions set in step X13 for the content to be advertised include genre specification, exclusion genre, season setting, target person (higher weight), meta word to be included (higher weight), Considering words that do not exist (excludes content that does not include) as search conditions, N items with the highest matching score value at the time of search, or those with a matching value above the threshold, will be the content to be advertised, and the results will be the target of advertisement provision Register in the setting information storage unit 120 (X16).

FIG. 9 shows the relationship between the advertisement target and the sympathy theme associated with it. A plurality of sympathy themes can be set to be associated with an advertisement target. However, it is assumed that the advertisement placement cost will change depending on the empathy theme that can be associated with one advertisement target or the number of contents that are associated with the empathy theme. In this example, "sympathetic theme 1" and "sympathetic theme 3" are associated with "advertising target 1", and "sympathetic theme 2" is associated with "advertising target 2". As a result, in this example, "advertising target 1" is placed in "contents 1, 3, 5" and "advertising target 2" is placed in "contents 2, 3".

The advertisement target setting information transmission request receiving unit 124 transmits the advertisement target setting information and the like to the user terminal 300 based on the request from the user terminal 300 (FIG. 2) (H4 in FIG. 4). In this way, the user terminal 300 (FIG. 2) can display advertisements in addition to content display (see FIG. 1).

Fig. 13 lists the results of extracting meta information from content (articles, C1 to C9) and advertisements (A1) that have a high matching score with the empathy theme "unwavering values." For example.

For example, as a calculation example of the matching score value, [Article Restaurant AAA Gourmet>Creative Cuisine] will be described as an example. The meta information of this content C1 is as follows.
・Fresh ingredients: 0.9 Local produce: 0.85 Seasons: 0.8 Uncompromising: 0.75 Consistent: 0.7 Commitment: 0.6 Chef: 0.4

Of the sympathetic theme "Unwavering values", the component words that are synonymous with the meta information of the above article (processed by name identification etc.) are
Unwavering: 1.0 Uncompromising: 0.9 Sticking to: 0.9
and
Matching score value = 0.75 x 0.9 (uncompromising) + 1.0 x 0.7 (no blurring) + 0.6 x 0.9 (sticky) = 1.915
is calculated as However, the method of calculating the score value is not limited to this.

Here, for example, consider a case where an advertiser places an advertisement for a "bag/purse specialty store" in A1 of FIG.

If no restrictions are specified, all of C1-C9 in FIG. 13 with high matching score values are listed.

On the other hand, since this advertisement target fashion>bags/wallets, if the advertiser does not want to place an advertisement in articles of the gourmet genre, "gourmet" is selected as the "excluded genre" in step X13 of the explanation of FIG. By specifying , it will be posted on C3, C4, C, 6, C7, and C9. Alternatively, by finely setting the designation of the "excluded genre" to "gourmet>seafood", it can be posted on C1-C7 and C9. Similarly, by specifying "gourmet" as the "excluded genre", "40's" as the "target person", and "antique" as the "excluded word", it can be published on C4, C6, and C7. Conditioning is not limited to this.

Here, a supplementary explanation will be given on the method of adding meta information to content.

As a method of adding meta information to content, the following method is generally used.
(1) Using methods such as morphological analysis for text information such as descriptions of target content (e.g. products), introductory articles, blogs, postings in posting columns, and postings on SNS (Social Networking Service) , words and phrases are extracted, and those representing the characteristics of the product are managed as tags.
(2) In the case of music content, in addition to tags obtained from text information related to music content (e.g. content of lyrics, introductory articles, etc.), for example, tempo of music signal, chronological change in loudness, frequency Information such as time-series changes in spectrum components, genre information, and information related to the characteristics of a singer's voice quality and singing style are managed as tags.
(3) In the case of video content, in addition to tags obtained from text information such as articles and scenarios related to video content, changes in color of video scenes, production, impression of BGM, character settings and lines of performers, voice actors , Manager, and other information determined from multiple factors are managed as tags.

FIG. 10 shows an example of an automatic tagging system. As the input text data of X101, descriptions, introductory articles, evaluation comments on bulletin boards, comments on contents on SNS, etc., in which details about contents are described, are assumed. At the same time, it is assumed that attributes such as content type, identification ID, and content name are added. X102 pre-processes this text information by removing unnecessary characters such as symbols, aligning uppercase and lowercase letters, and aligning half-width and full-width characters, and then performs morphological analysis on X103, enabling extraction at the word level. become. Here, an output example by the MeCab morphological analysis engine will be described as an example of morphological analysis. For example, morphological analysis of the input text "this cushion is fluffy and cute" (Fig. 11A) yields the output shown in Fig. 11B. If only "adjective" is extracted, the words "cushion", "fluffy" and "cute" are extracted as the output of the keyword extraction X103 (FIG. 11(C)). The user dictionary X104 may be referred to for keyword extraction.

There are various methods for obtaining the degree of importance of words in a document, such as using LDA (Latent Dirichlet Allocation) and vectors matching the meaning of words. Here, an example using a technique called TF-IDF will be described (https://ja.m.wikipedia.org/wiki/Tf-idf). In TF-IDF, TF represents word frequency (the number of times a specific word appears in a document), and IDF represents inverse document frequency (the natural logarithm of the number of documents containing the document in the entire corpus). It has the following meanings.
TF: The more frequently a word appears in document dd, the more important it is to express the characteristics of that document. IDF: Generally, words such as "a" and "the" that appear in any document are not important. -IDF represents "importance of word ww in document dd". This TF-IDF is a quantity determined for each word w and document dd. IDF(w)
Here, in order to obtain the importance of words that appear for each content type, sentences with the same content attribute (pg) are counted as the same sentence and the TF-IDF value is used.
TF - IDF (w, pg) = TF (w, pg) x IDF (w)
The degree of importance of a word in the type of content obtained in this manner indicates that the greater the numerical value, the higher the degree of importance. In FIG. 10, the importance score value of a word is calculated by generating statistical information X105 and calculating importance score value X106.

The keywords extracted from each text sentence are stored together with the relationship with the value n_count(w) of the number of times the keyword w appears in the sentence (X107). For example, it is assumed that the keywords "cushion", "fluffy" and "cute" are extracted once each as a result of extraction from the text related to "content name A". An output example of the keyword extraction X3 in FIG. 10 in that case is as follows, as shown in FIG. 12(A).
Content name A: Cushion: 1, Fluffy: 1, Cute: 1
In the tag processing X107 of FIG. 10, the number of extracted words is counted for each content name added to the input text X101. For example, as shown in FIG. 12B, the keyword extraction result of the text input for "content name A" different from the above extraction result is content name A: pouch: 1, soft: 1, cute: 1, fluffy: 2
year,
sum_count(w)=Σn_count(w)
is calculated (FIG. 12(C)), the tabulation result in the tag processing X107 is as follows, as shown in FIG. 12(D).
Content name A: Fluffy: 3, Cute: 2, Light: 1, Cushion: 1, Pouch: 1
Furthermore, in the aggregation tagging process X108 in FIG. 10, from the aggregation result of the keywords related to the content name A, words that are unnecessary as tags and words whose number of occurrences is less than a certain value are deleted (filtering process X109), and remaining For word w, a score value (word_score(w)=func(weight_score(w) , sum_count(w)) (FIG. 12(E)) to determine the keywords.For example, the importance score of each keyword is calculated as word_score(w)=func(weight_score(w)×sum_count(w)). (FIG. 12(F)), the value is more than a certain value and the number of corresponding keywords is less than the upper limit is added as an information tag. The score values of the keywords may be normalized so that the total value becomes 1. The tags are output as tags as shown in FIG.
Content name A: fluffy: 0.53, cute: 0.32, light: 0.15

Contents can be searched using these meta information. In this embodiment, empathy themes are assigned to content based on this meta-information.

Characteristic words of advertisement targets and constituent element information of sympathetic themes can be generated by a similar method, but the present invention is not limited to this.

Next, a specific example of the sympathy theme of this embodiment will be given for supplementary explanation. FIG. 14 lists a plurality of specific examples of empathy themes. In this example, meta-information (meta-words) is assigned comprehensively to each sympathetic theme, but each sympathetic theme is divided into genres such as general, gourmet, travel, etc., and meta-information is assigned to each genre to characterize it. good In this manner, metaword sets may be selected according to their genre when matching content and advertisements.

In FIG. 15, related phrases (sub-themes) are provided separately from empathy themes to enable flexible processing. Related phrases (sub-themes) are also matched with content and advertisements. For example, if a matching score is high for a sub-theme, a sympathetic theme related to the sub-theme may be selected. In the embodiment, the empathy theme is a name (word/phrase, sentence) for processing that represents a group of related phrases, and the empathy theme itself may not have tag information, or may have tag information. You can give it. In the example of FIG. 15, the empathy theme is "unwavering values", and the related phrases (sub-themes) are "unwavering values" (same as the empathy theme), "unwavering self", and "not being swayed by others". , "I can do my best to achieve my ideals." A plurality of related phrases (sub-themes) are provided to enable multifaceted characterization, and switching may be performed according to conditions such as genre.

FIG. 16 shows examples of metawords, which can be given their attributes and categories. Word quick-composition and categories may be used to adapt to the content.

FIG. 17 is a diagram for explaining an example of advertisement information. In this example, the advertisement information consists of an advertisement title and an advertisement description. In this example, the score value is the maximum value of matching scores with related phrases of each common theme, but it may be an average value considering the weight of each related phrase with respect to the score value of each related phrase. "I want to be beautiful from the inside", "I want to go on a diet", and "I want to follow the basic diet" are associated with the advertisement in FIG. 17 based on the degree of matching.

FIG. 18 is an example of metawords and score values obtained from advertisement information. Metawords extracted from descriptions, etc., are calculated by methods such as TF-IDF for each genre of advertisement so that the score value of characteristic words for each genre is high. score value).

FIG. 19 shows examples of empathy themes and related phrases. Empathy theme: This is an example where two related phrases are defined for “I want to be beautiful from the inside”, “becoming beautiful from the inside” and “polishing the inside”. If a tag is matched, it is also considered to be matched to its parent empathy tag. In addition, the empathy theme: "I want to diet" is defined with the related phrase "I can lose weight without difficulty", and the empathy theme: "Faithful to the basics of eating habits" is defined with the related phrase "regular eating habits". Metawords are assigned to these related phrases.

FIG. 20 shows a description example of the meta information of the related phrase "becoming beautiful from the inside out". In FIG. 20(A), the metawords assigned to "beautiful from the inside out" are arranged in descending order of relevance, and the score value is defined by a separately defined weighting function for the sorting order. You can associate them as a matrix for each order from the beginning. Also, it may be explicitly displayed as a table as shown in FIG. 20(B), and the pairs of metawords and weights may be explicitly displayed as shown in FIG. 20(C).

FIG. 21 shows examples of calculation of matching scores for the empathy theme "I want to be beautiful from the inside out"/related phrase "I want to be beautiful from the inside out", the empathy theme "I want to lose weight"/related phrase "I want to lose weight without difficulty", and , the sympathetic theme ``I can lose weight without difficulty'' / the related phrase ``regular eating habits''. Matching scores may be calculated as shown in FIGS. 21(A), (B) and (C). The higher the matching score value, the higher the degree of matching (the value may be 1 or more). The greater the divergence value (divergence score value), the lower the degree of matching.

According to this embodiment, even if the advertiser does not finely adjust the meta information for the advertisement, the advertiser selects the theme that the advertiser wants to publish, and the content that matches the theme is specified and published. be able to.

Next, a modified example of the invention will be described. FIG. 22 schematically shows this modification, and in this figure, the parts corresponding to those in FIG. In FIG. 22, the advertiser designates a sympathetic theme from the sympathetic theme designating section 126 for advertisement. This designation may be performed using a search means or using a menu. The matching degree/divergence calculating unit 127 calculates the matching degree/divergence by the method shown in FIG. 21 and displays it to the advertiser, but is not limited to this. The advertiser may refer to the degree of coincidence/divergence to determine the sympathetic theme, and may re-input the sympathetic theme. The determined empathy theme is registered in the advertisement provision target setting information storage unit 120 together with other setting information.

According to this modification, even if the advertiser does not finely adjust the meta information for the advertisement, the advertiser can select the sympathetic theme that the advertiser wants to publish, and specify and publish the content that matches the theme. can be done.

This completes the description of the embodiment.

It should be noted that the present invention is not limited to the above-described embodiments, and various modifications can be made without departing from the scope of the invention.

100 Advertisement target setting information management server 102 Content meta information extraction unit 104 Content management information storage unit 104A Meta information storage unit 104B Sympathy theme storage unit 106 Sympathy theme component element information extraction unit 108 Sympathy theme component element information storage unit 110 content sympathy theme determination unit 112 advertisement information input unit 114 advertisement sympathy theme determination unit 116 advertisement target setting information adjustment unit 120 advertisement target setting information storage unit 122 content selection unit 124 advertisement target setting information transmission request reception unit 126 Advertisement sympathetic theme designating unit 127 Matching degree/divergence calculating unit 200 Web server 300 User terminal 400 Communication network 1000 Computer 1001 CPU
1002 main memory 1003 input/output interface (input/output bus)
1004 external regulation device 1005 application

Claims (19)

an advertisement target candidate content metaword association data holding means for holding advertisement target candidate content metaword association data for associating one or more metawords with an advertisement target candidate content;
Advertisement feature description for associating, with each of a plurality of advertisement characterizing phrases prepared in advance for individually describing a feature of an advertisement, a group of characterizing phrases prepared in advance for characterizing each of the advertisement characterizing phrases. advertising characterizing phrase group association data holding means for holding phrase characterizing phrase group association data;
The metaword association data for the candidate content for advertisement provision held in the metaword association data holding means for the candidate content for advertisement provision and the advertising feature held in the characterizing phrase group association data for advertisement feature description phrase an advertisement feature description phrase association means for associating one or more of the advertisement feature description phrases with each of at least a portion of the candidate content for advertisement presentation based on the characterization phrase group association data for advertisement presentation target content;
Advertisement target content by obtaining one or more of the advertisement characterizing phrases corresponding to the specified advertisement and selecting the advertisement target content based on the association with the obtained advertisement characterizing phrase An advertisement target setting information management device, comprising: advertisement target content selection information generating means for generating selection information. 2. The advertisement provision target setting information management device according to claim 1, wherein the advertisement feature description phrase is an advertisement theme. 3. The advertisement target setting information management device according to claim 1, wherein the advertisement target candidate content is content displayed on the web. The advertisement provision target setting information management device according to any one of claims 1 to 3, wherein the advertisement feature description phrase is composed of a word, phrase or sentence. The advertisement provision target setting information management device according to any one of claims 1 to 4, wherein the meta word is composed of a word or a phrase. The advertisement provision target setting information management device according to any one of claims 1 to 5, wherein the characterizing phrase group is composed of one or more words, phrases or sentences. 7. The metaword association data for candidate content for advertisement provision specifies one or more metawords associated with each of the candidate contents for advertisement provision and their respective importance levels. 2. The advertisement provision target setting information management device described in . 8. Said characterizing phrase group association data for advertisement characterizing phrases specifies, for each of said advertising characterizing phrases, phrases in the associated characterizing phrase group and their importance. The advertisement provision target setting information management device according to any one of the above. The advertisement target setting information management apparatus according to any one of claims 1 to 8, further comprising means for generating said advertisement target candidate content meta word association data based on information relating to each of said advertisement target candidate contents. means for inputting advertising target information;
10. The advertisement provision target setting information management apparatus according to claim 1, further comprising advertisement feature description phrase determination means for determining an advertisement feature description phrase of the advertisement based on the inputted advertisement target information. The advertising feature descriptive phrase determination means extracts one or more feature phrases from the advertisement target information, and the advertisement features held in the advertisement feature descriptive phrase component phrase association data holding means. 11. The advertisement providing target setting information management device according to claim 10, wherein the corresponding advertisement feature descriptive phrase is determined based on the descriptive phrase constituent element phrase. Advertisement feature description for candidate content for provision of advertisement, which associates with candidate content for provision of advertisement one or more selected from a plurality of characterization description phrases for advertisement prepared in advance for independently describing the characteristics of each advertisement. advertising feature description phrase association data holding means for advertisement target candidate content holding phrase association data;
Advertisement information input means for inputting advertisement target information;
Advertisement feature description phrase determination means for determining an advertisement feature description phrase of the advertisement based on the inputted advertisement target information;
The advertising characteristic descriptive phrase determined by the advertising characteristic descriptive phrase determination means for the designated advertisement, and the advertisement provision target candidate held in the advertisement provision target candidate content advertisement feature description phrase association data holding means. advertisement target content selection information generating means for selecting the advertisement target content based on the advertisement feature description word association data for content and generating the advertisement target content selection information. Information management device. a selection means for a user to select an advertisement characterizing phrase;
The advertisement provision according to any one of claims 10 to 12, further comprising matching level output means for outputting a matching level based on the inputted advertisement target information and the advertisement feature description phrase selected by the selecting means. Target setting information management device. a selection means for a user to select an advertisement characterizing phrase;
The advertisement provision according to any one of claims 10 to 12, further comprising deviation degree output means for outputting a deviation degree based on said inputted advertisement target information and said advertisement feature description phrase selected by said selection means. Target setting information management device. a user device;
Advertisement target setting information supply for supplying the advertisement target content selection information generated by the advertisement target setting information management device according to any one of claims 1 to 14 to the user based on a request from the user device. a server device;
a server that supplies content to the user device based on a request from the user device;
The user device displays a list of advertisements based on the content selection information supplied from the advertisement target setting information supplying server device in addition to the contents supplied from the server. Content-linked advertising system. a step in which the metaword association data for advertisement target candidate content holding means holds metadata for advertisement target candidate content that associates one or more metawords with the advertisement target candidate content;
Characterizing phrase group association data storage means for advertising feature description phrases, for each of a plurality of advertisement feature description phrases prepared in advance for independently describing a feature of an advertisement, to characterize each of the advertisement feature description phrases holding characterization phrase group association data for advertising characterization phrases respectively associating pre-prepared characterization phrase groups to
The advertising feature description phrase association means for advertisement target content candidate content metaword association data and the advertisement feature description phrase characterizing phrase held in the advertisement provision target candidate content metaword association data holding means. One or more of the advertising characteristic descriptive phrases are associated with each of the at least a part of the candidate contents for the advertisement provision based on the characteristic phrase group association data for the advertisement characteristic descriptive phrases held in the group association data holding means. a step;
Advertisement target content selection information generating means acquires one or more of the advertisement characteristic description phrases corresponding to the specified advertisement, and provides the advertisement based on association with the acquired advertisement characteristic description phrases. and selecting target content to generate advertisement target content selection information. Advertisement provision target candidate content advertisement feature description phrase association data holding means stores one or a plurality of advertisement feature description phrases selected from a plurality of advertisement feature description phrases prepared in advance for independently describing features of advertisements, respectively. holding advertisement feature description word association data for candidate advertisement serving content to be associated with candidate advertisement serving content;
an advertisement target information input means inputting advertisement target information;
a step in which an advertisement characterizing phrase determining means determines an advertisement characterizing phrase of the advertisement based on the inputted advertisement target information;
Advertisement target content selection information generation means stores, for a designated advertisement, the advertisement feature description phrase determined by the advertisement feature description phrase determination device and advertisement feature description phrase association data storage means for advertisement target candidate content. selecting the content to be provided with the advertisement and generating selection information for the content to be provided with the advertisement based on the advertisement feature description phrase association data for the candidate content for the advertisement provided and held in the Provision target setting information management method. the computer,
an advertisement target candidate content metaword association data holding means for holding advertisement target candidate content metaword association data for associating one or more metawords with an advertisement target candidate content;
Advertisement feature description for associating, with each of a plurality of advertisement characterizing phrases prepared in advance for individually describing a feature of an advertisement, a group of characterizing phrases prepared in advance for characterizing each of the advertisement characterizing phrases. advertising characterizing phrase group association data holding means for holding phrase characterizing phrase group association data;
The metaword association data for the candidate content for advertisement provision held in the metaword association data holding means for the candidate content for advertisement provision and the advertising feature held in the characterizing phrase group association data for advertisement feature description phrase an advertisement serving content advertising feature description phrase associating means for associating one or more of the advertisement serving content description phrases with each of at least a portion of the advertisement serving candidate content based on descriptive phrase characterizing phrase group association data; and ,
Advertisement target content by obtaining one or more of the advertisement characterizing phrases corresponding to the specified advertisement and selecting the advertisement target content based on the association with the obtained advertisement characterizing phrase A computer program for managing advertisement target setting information used for configuring as an advertisement target content selection information generating means for generating selection information. the computer,
Advertisement feature description for candidate content for provision of advertisement, which associates with candidate content for provision of advertisement one or more selected from a plurality of characterization description phrases for advertisement prepared in advance for independently describing the characteristics of each advertisement. Advertisement feature description phrase association data holding means for advertisement target candidate content holding phrase association data;
advertising information input means for inputting advertising target information;
Advertisement feature description phrase determination means for determining an advertisement feature description phrase of the advertisement based on the inputted advertisement target information;
The advertising characteristic descriptive phrase determined by the advertising characteristic descriptive phrase determination means for the designated advertisement, and the advertisement provision target candidate held in the advertisement provision target candidate content advertisement feature description phrase association data holding means. Advertisement target setting used for configuring as advertisement target content selection information generation means for selecting the above-mentioned advertisement target content based on the advertisement feature description word association data for content and generating advertisement target content selection information A computer program for information management.

Images