JP5086303B2 - Advertisement providing device - Google Patents

Description

  The present invention relates to a technique for providing advertisement information via a network such as the Internet.

  As a technique for providing an effective advertisement to a user who browses a page of a site on the Internet, there is a technique for providing an advertisement for a product that matches (matches) the content (content) of a page, called content matching ( For example, see Patent Document 1.)

  Since the user is interested in the contents of the page, he / she browses, so the user is more likely to be interested in advertising for the product related to the content of the page to be browsed, which may lead to the purchase of the product. It is based on the idea that it is expensive.

JP 2008-102174 A

  As described above, the content matching method is the mainstream for providing advertisement information, but only text data is generally targeted for content matching. That is, a word / phrase extracted from text data included in the content is a content match target.

  In this regard, recently, emoticons using illustration characters and emoticons that represent human faces by arranging normal characters are often used in e-mails, blogs, bulletin boards, etc., but these are subject to content matching. I can't. A single pictogram or emoticon is referred to as “pictogram etc.”.

  In addition, continuous pictograms and the like that express a specific meaning (word) by continuating a plurality of pictograms and emoticons have come to be used in many cases, but these cannot be used as content matching targets.

  In these articles such as blogs and bulletin boards, pictograms etc. are the parts that show the true intentions that the author strongly insists, so the accuracy of the advertisement information provided can not be raised because it can not be targeted for content matching is there.

  The present invention has been proposed in view of the above-described conventional problems, and an object of the present invention is to provide an advertisement providing apparatus that can select advertisement information corresponding to single or continuous pictograms. is there.

In order to solve the above problems, according to the present invention, as described in claim 1, an article browsing request receiving unit that receives an article browsing request from a user terminal, and an article content indicated by the article browsing request is stored in a content database. From the acquired article acquisition means and the acquired article content, refer to the dictionary of single pictograms and the dictionary of continuous pictograms, extract single pictograms or continuous pictograms, etc. Text part feature word extraction that extracts feature words from text parts excluding single pictograms or continuous pictograms in the article content when there are two or more types of corresponding word acquisition means and single pictograms or continuous pictograms extracted The similarity between the means and the extracted single pictogram or the word corresponding to the continuous pictogram and the feature word of the extracted text part is determined. , A pictogram or the like corresponding word specifying means for squeezing the word corresponding to a single pictogram or the like or continuous pictogram such as one based on the word corresponding to the extracted single pictogram or the like or continuous pictograms, etc., advertisements referring to the advertisement database matching The gist of the present invention is an advertisement providing apparatus including advertisement matching means for performing advertisement, advertisement embedding means for embedding an advertisement in article content, and article page transmitting means for transmitting a page of article content embedded with an advertisement to a request source.

Further, as described in claim 2, a method for providing an advertisement advertisement providing device performs a post browsing request accepting step of accepting an article browsing request from the user terminal, the article contents indicated by the articles viewing request from the content database From the acquired article acquisition process and the acquired article content, refer to the dictionary of single pictograms and the dictionary of continuous pictograms, extract single pictograms or continuous pictograms, and extract and handle pictograms to acquire the corresponding words A word acquisition step and a text partial feature word extraction step of extracting feature words from a text portion excluding single pictograms or continuous pictograms of article contents when there are two or more types of extracted single pictograms or continuous pictograms And the word corresponding to the extracted single pictogram or continuous pictogram etc. and the feature word of the extracted text part And, a pictogram or the like corresponding word specifying step to narrow the word corresponding to a single pictogram or the like or continuous pictogram such as one based on the word corresponding to the extracted single pictogram or the like or continuous pictograms, etc., advertisement by referring to the advertisement database An advertisement providing control method comprising: an advertisement matching process for performing matching; an advertisement embedding process for embedding an advertisement in article content; and an article page transmission process for transmitting an article content page embedded with an advertisement to a request source. it can.

  In the advertisement providing apparatus of the present invention, advertisement information corresponding to single or continuous pictograms can be selected.

It is a figure which shows the structural example of the system concerning one Embodiment of this invention. It is a figure which shows the data structure example of a content database. It is a figure which shows the data structure example of a dictionary, such as a single pictogram. It is a figure which shows the example of a data structure of a dictionary, such as a continuous pictograph. It is a figure which shows the data structure example of a word dictionary. It is a figure which shows the example of a data structure of a synonym dictionary. It is a figure which shows the data structure example of an advertisement database. It is a figure which shows the hardware structural example of a blog / bulletin board server. It is a sequence diagram which shows the process example of embodiment. It is a figure which shows the example of the browsing screen with which the advertisement was synthesize | combined.

  Hereinafter, preferred embodiments of the present invention will be described.

<Configuration>
FIG. 1 is a diagram showing a configuration example of a system according to an embodiment of the present invention.

  In FIG. 1, a plurality of user terminals 2 such as a PC (Personal Computer), a mobile phone, and a PDA (Personal Digital Assistants) operated by a user are connected to a network 1 such as the Internet. The user terminal 2 includes a general browser (Web browser) 21. The browser 21 performs request / acquisition / display of page data described in a language such as HTML (Hyper Text Markup Language), transmission of form data, and the like according to HTTP (Hyper Text Transfer Protocol) which is a standard protocol of the Internet. It has a function.

  On the other hand, connected to the network 1 is a blog / bulletin board server 3 for managing browsing / posting of blogs / bulletin boards in response to access from the browser 21 of the user terminal 2 operated by the user.

  The blog / bulletin board server 3 includes, as function units, an article browsing request accepting unit 31, an article acquiring unit 32, a pictogram and the like extracting / corresponding word acquiring unit 33, a text partial feature word extracting unit 34, a pictogram and the like corresponding word specifying unit 35, and an advertisement. A matching unit 36, an advertisement embedding unit 37, and an article page transmission unit 38 are provided. These functional units are realized by computer programs executed on hardware resources such as a CPU (Central Processing Unit), a ROM (Read Only Memory), and a RAM (Random Access Memory) of a computer constituting the blog / bulletin board server 3. It is what is done. These functional units do not need to be arranged on a single computer, and may be distributed as necessary.

  Further, a content database 301, a single pictographic dictionary 302, a continuous pictographic dictionary 303, a word dictionary 304, a synonym dictionary 305, and an advertisement database 306 are provided as a dictionary or database to be referred to / updated by the blog / bulletin board server 3. . These dictionaries and the like systematically hold predetermined data on a storage medium such as an HDD (Hard Disk Drive) in a computer that holds the dictionaries and the like.

  FIG. 2 is a diagram showing an example of the data structure of the content database 301, and has items such as “registration date”, “registrant user ID”, and “article content”. “Registration date” is the date and time when the article was registered (published). The “registrant user ID” is the user ID of the user who registered the article. “Article content” is data of the content of an article, and includes text, images, sounds, and the like.

  FIG. 3 is a diagram showing an example of the data structure of the single pictogram dictionary 302, and has items such as “pictogram etc.”, “code”, and “word”. “Emoji” or the like is an emoticon representing one character or one meaning. “Code” is information for identifying a pictograph or the like. “Word” is a word corresponding to a pictograph or the like.

  FIG. 4 is a diagram showing an example of the data structure of the continuous pictogram dictionary 303, and includes items such as “continuous pictograms”, “words”, “appearance count (update date and time)”, “region”, and the like. “Continuous pictograms” are a plurality of continuous pictograms or emoticons. A “word” is a word corresponding to a continuous pictograph or the like. “Number of appearances (update date / time)” is the number of times of appearance by the analysis and the last update date / time. The “region” is a region where a user who has written an article in which a continuous pictograph or the like appears is located.

  FIG. 5 is a diagram showing an example of the data structure of the word dictionary 304, and has items such as “word” and “part of speech”. A “word” is a word that becomes a headline. “Part of speech” is the part of speech of the word.

  FIG. 6 is a diagram showing an example of the data structure of the synonym dictionary 305, and has items such as “word” and “synonym”. A “word” is a word that becomes a headline. A “synonym” is other word (s) that are similar to the word.

  FIG. 7 is a diagram illustrating an example of the data structure of the advertisement database 306, and includes items such as “advertisement ID”, “keyword”, and “advertisement content”. “Advertisement ID” is information for identifying an advertisement. The “keyword” is a phrase that is associated with the advertisement by content matching. “Advertising content” is data of advertising content, and includes text, images, sounds, and the like. Instead of holding actual data as “advertising content”, a reference to the storage location of actual data may be held.

  Returning to FIG. 1, the article browsing request receiving unit 31 has a function of receiving an article browsing request from the browser 21 of the user terminal 2 and performing control until page transmission to the browser 21 of the user terminal 2.

  The article acquisition unit 32 has a function of acquiring article content from the content database 301 in response to a request from the article browsing request reception unit 31.

  The pictogram extraction / corresponding word acquisition unit 33 refers to the single pictogram dictionary 302 and the continuous pictogram dictionary 303 in response to a request from the article browsing request reception unit 31, and searches for single pictograms or continuous pictograms from the article content. It has a function of extracting and acquiring a corresponding word.

  The text partial feature word extraction unit 34 refers to the word dictionary 304 in response to a request from the pictogram extraction / corresponding word acquisition unit 33 when there are two or more types of single pictograms or continuous pictograms extracted from the article content. Thus, it has a function of extracting feature words from a text portion excluding single pictograms or continuous pictograms of article contents.

  The pictogram corresponding word specifying unit 35 refers to the synonym dictionary 305, the word corresponding to the single pictogram or the like or the continuous pictogram extracted by the pictogram etc. extraction / corresponding word acquisition unit 33, and the text partial feature word extraction unit 34. It has a function of determining similarity to the feature word of the text part extracted in step 1, and narrowing down the words corresponding to single pictograms or continuous pictograms to one.

  The advertisement matching unit 36 uses the advertisement database based on words corresponding to single pictograms or continuous pictograms extracted by the pictogram etc. extraction / corresponding word acquisition unit 33, or words narrowed down by the pictogram corresponding word specifying unit 35. Reference numeral 306 denotes a function for performing advertisement matching.

  The advertisement embedding unit 37 has a function of embedding advertisements in the article content in response to a request from the article browsing request receiving unit 31.

  The article page transmission unit 38 has a function of transmitting an article content page in which an advertisement is embedded in the browser 21 of the requesting user terminal 2.

  FIG. 8 is a diagram illustrating a hardware configuration example of the blog / bulletin board server 3.

  In FIG. 8, the blog / bulletin board server 3 is connected to a CPU 3002, ROM 3003, RAM 3004, NVRAM (Non-Volatile Random Access Memory) 3005, I / F (Interface) 3006, and I / F 3006 connected to a system bus 3001. Also provided are an I / O (Input / Output Device) 3007 such as a keyboard, mouse, monitor, CD / DVD (Compact Disk / Digital Versatile Disk) drive, HDD 3008, NIC (Network Interface Card) 3009, and the like. M is a medium (recording medium) such as a CD / DVD in which a program or data is stored.

<Operation>
FIG. 9 is a sequence diagram showing a processing example of the above embodiment.

  In FIG. 9, when the user of the user terminal 2 browses the blog or the bulletin board, the browser 21 of the user terminal 2 accesses the article browsing request reception unit 31 of the blog / bulletin board server 3 to make a page request (step S101). . For the page request, a message including a GET method according to HTTP which is a standard protocol of the Internet and a request URI (Uniform Resource Indicator) is transmitted from the browser 21 of the user terminal 2 to the article browsing request receiving unit 31 of the blog / bulletin board server 3. Is done.

  In response to this, the article browsing request receiving unit 31 of the blog / bulletin board server 3 makes an article acquisition request to the article acquiring unit 32 (step S102), and the article acquiring unit 32 acquires the corresponding article from the content database 301 (step S102). S103) and hand it over to the article browsing request accepting unit 31 (step S104).

  Next, the article browsing request reception unit 31 delivers the article content to the pictogram extraction / corresponding word acquisition unit 33 (step S105).

  The pictogram extraction / corresponding word acquisition unit 33 refers to the single pictogram dictionary 302 and the continuous pictogram dictionary 303 with respect to the article content passed from the article browsing request reception unit 31 to search for single pictograms or continuous pictograms. Extract (step S106). That is, the article content is searched using the single pictogram or the continuous pictogram registered in the single pictogram dictionary 302 or the continuous pictogram dictionary 303 as a key, or the article content is scanned and the single pictogram or the continuous is scanned. It is determined whether or not pictograms appear, and single pictograms or continuous pictograms that have appeared are extracted.

  Next, the pictogram extraction / corresponding word acquisition unit 33 acquires the extracted single pictogram or the like or a word corresponding to the continuous pictogram (corresponding word) from the single pictogram dictionary 302 or the continuous pictogram dictionary 303 (step S107).

  Next, when there are two or more types of single pictograms or continuous pictograms extracted from the article contents, the pictogram etc. extraction / corresponding word acquisition section 33 delivers the article contents and the corresponding words to the text partial feature word extraction section 34 (step S108).

  In response to this, the text part feature word extraction unit 34 refers to the word dictionary 304 and extracts a feature word from the text part excluding single pictographs or continuous pictographs of the article content (step S109). The feature word is extracted by, for example, comparing the character string of the text part of the article content and the word registered in the word dictionary 304 by using a longest match method or the like, and using a word with a high matching frequency as a feature word. decide. Then, the text partial feature word extraction unit 34 delivers the corresponding word passed from the pictogram extraction / corresponding word acquisition unit 33 and the extracted feature word to the pictorial character correspondence word specifying unit 35 (step S110).

  In response to this, the corresponding word specifying unit 35 such as a pictogram refers to the synonym dictionary 305 to determine the similarity between the plurality of corresponding words and the feature words of the text part extracted by the text part feature word extracting unit 34, Words corresponding to single pictograms or continuous pictograms are narrowed down to one (step S111). That is, for each corresponding word, the synonym dictionary 305 is referred to using one of the corresponding word or feature word as a key, and whether or not the other word is similar is determined based on whether or not the other word is registered as a synonym. By setting synonyms in the synonym dictionary 305 in descending order of similarity, even if a plurality of corresponding words are determined to be similar to a feature word, it can be determined which is more similar. Can be squeezed. Then, the corresponding word specifying unit 35 such as a pictograph hands over the corresponding word narrowed down to one to the text partial feature word extracting unit 34 (step S112). The text partial feature word extraction unit 34 passes the corresponding word to the pictogram extraction / correspondence word acquisition unit 33 (step S113).

  The pictogram extraction / correspondence word acquisition unit 33 delivers the corresponding word extracted by itself or the word narrowed down by the pictogram correspondence word specifying unit 35 to the article browsing request reception unit 31 (step S114).

  Next, the article browsing request receiving unit 31 delivers the corresponding word to the advertisement matching unit 36 (step S115).

  In response to this, the advertisement matching unit 36 performs advertisement matching with reference to the advertisement database 306 based on the passed corresponding word (step S116). That is, the keyword column of the advertisement database 306 is searched using the corresponding word as a key to find a hit advertisement. The number of advertisements is not limited to one, but can be a predetermined number that can be embedded in the browsing page. When more than a predetermined number of advertisements are hit, a predetermined number of advertisements are determined from the top based on the hit rate or the like. When the advertisement is not hit at all or when it is less than the predetermined number, the default advertisement is used.

  Next, the advertisement matching unit 36 acquires the data of the hit advertisement from the advertisement database 306 (step S117), and delivers it to the article browsing request receiving unit 31 (step S118).

  The article browsing request acceptance unit 31 delivers the article content, the advertisement data, and the destination address to the advertisement embedding unit 37 (step S119). The destination address is a source address (IP address, port number) at the time of page request from the browser 21 of the user terminal 2 (step S101).

  In response, the advertisement embedding unit 37 embeds the advertisement in the article content to generate page data (step S120), and delivers the page data to the article page transmission unit 38 (step S121). The advertisement is embedded in the case where the advertisement data itself is embedded in the page data by HTML or the like and in the case where a reference to the advertisement data is embedded.

  Next, the article page transmission unit 38 transmits page data to the browser 21 of the user terminal 2 indicated by the destination address (step S122).

  The browser 21 of the user terminal 2 displays page data (step S123). When the reference to the advertisement data is embedded in the page data, the display is completed by accessing any server holding the advertisement data from the browser 21 of the user terminal 2. FIG. 10 is a diagram illustrating an example of a browsing screen 201 on which advertisements are combined. The advertisements are displayed in an advertisement area 203 below the article area 202. In this case, an advertisement selected based on a word corresponding to a pictograph included in the article region 202 (single pictograph, continuous pictograph, etc.) is displayed. Note that the layout of the browsing screen is not limited to that shown in the figure, and may be arbitrary.

<Summary>
As described above, according to the present embodiment, it is possible to select advertisement information corresponding to single or continuous pictograms, etc., and the advertisement conforms to the content that the author of the article intends to emphasize and has a high advertising effect. I can expect.

  The present invention has been described above by the preferred embodiments of the present invention. While the invention has been described with reference to specific embodiments, various modifications and changes may be made to the embodiments without departing from the broad spirit and scope of the invention as defined in the claims. Obviously you can. In other words, the present invention should not be construed as being limited by the details of the specific examples and the accompanying drawings.

DESCRIPTION OF SYMBOLS 1 Network 2 User terminal 21 Browser 3 Blog / Bulletin board server 31 Article browsing request reception part 32 Article acquisition part 33 Pictogram etc. extraction / correspondence word acquisition part 34 Text part feature word extraction part 35 Pictogram etc. correspondence word specification part 36 Advertisement matching part 37 Advertisement embedding unit 38 Article page transmission unit 301 Content database 302 Single pictographic dictionary 303 Continuous pictographic dictionary 304 Word dictionary 305 Synonym dictionary 306 Advertising database

Claims (2)

An article browsing request receiving means for receiving an article browsing request from a user terminal;
Article acquisition means for acquiring the article content indicated by the article browsing request from the content database;
From the acquired article content, refer to a dictionary of single pictograms and a dictionary of continuous pictograms, extract single pictograms or continuous pictograms, etc., and extract pictograms and corresponding word acquisition means for acquiring corresponding words;
A text part feature word extraction means for extracting a feature word from a text part excluding single pictograms or continuous pictograms of the article content when there are two or more types of extracted single pictograms or continuous pictograms;
A word corresponding to an extracted single pictogram or continuous pictogram etc. and a word corresponding to the extracted text part feature word are determined to narrow down the word corresponding to the single pictogram or continuous pictogram etc. Specific means,
Based on the words corresponding to the extracted single pictograms or continuous pictograms, etc., an ad matching means for performing ad matching with reference to the ad database,
An advertisement embedding means for embedding an advertisement in the article content;
An advertisement providing apparatus comprising article page transmission means for transmitting a page of article contents embedded with an advertisement to a request source. An advertisement providing method performed by an advertisement providing apparatus,
An article browsing request reception process for receiving an article browsing request from a user terminal;
An article acquisition process for acquiring the article content indicated by the article browsing request from the content database;
From the acquired article content, refer to the dictionary of single pictograms and the dictionary of continuous pictograms, extract single pictograms or continuous pictograms, etc., and extract the corresponding pictograms etc.
A text part feature word extraction step of extracting a feature word from a text part excluding a single pictogram or continuous pictogram of the article content when there are two or more types of extracted single pictograms or continuous pictograms; and
A word corresponding to an extracted single pictogram or continuous pictogram etc. and a word corresponding to the extracted text part feature word are determined to narrow down the word corresponding to the single pictogram or continuous pictogram etc. Specific process,
An ad matching step of performing ad matching by referring to an ad database based on the extracted single pictograms or words corresponding to continuous pictograms,
An ad embedding process for embedding an advertisement in the article content;
An article providing method comprising: an article page transmitting step of transmitting an article content page embedded with an advertisement to a request source.

Images