KR20230046041A - Keyword based online advertisement matching system and online advertisement method - Google Patents

Abstract

The present invention relates to a keyword-based advertisement matching method of online content and an advertisement matching system using the same. The method includes the steps of: indexing online content to generate content indexing data; extracting one or more primary keywords from the indexing data; filtering words of negative images among the extracted main keywords; determining one or more commercial keywords related to the primary keywords obtained by filtering the words of negative images; and processing an advertisement corresponding to the determined commercial keyword to be included in the content.

Description

Keyword-based online advertisement matching system and online advertisement method {KEYWORD BASED ONLINE ADVERTISEMENT MATCHING SYSTEM AND ONLINE ADVERTISEMENT METHOD}

The present invention relates to a keyword-based online advertisement matching system and an online advertisement method.

BACKGROUND OF THE INVENTION [0002] With the development of information and communication technology, online-based content creation is becoming more active. Various website operators produce various online contents such as news articles, columns, blogging, and videos, post advertisements in the contents, and generate advertisement revenue when site visitors click advertisements included in the contents.

Therefore, content producers need to expose content to a large public in order to increase advertising efficiency, and to this end, content distribution such as search engine optimization is becoming important.

In the case of a general search site such as Google, search engines import online contents in advance through crawling, and when a search word is entered, the corresponding data is output from the collected contents. In this case, their contents are actually In many cases, it is not searched by search engines, and even if it is searched, it is often pushed out of the search ranking over time and cannot attract the attention of the general public who performed the search.

In addition to this, even if their content is searched by search engines, content producers can find out whether the traffic to their website has increased as a result of the actual search, how much their content is being consumed, and what content is included in the website or content. There was a limit to getting information about how many ads were clicked.

Therefore, a method for improving the value of the content and evaluating this improvement in the value of the content by exposing the produced content to more people, and exposing the advertisement included in it to consumers together to generate revenue from the content, and The system is desperately needed.

An object to be solved by the present invention is to provide a method and system for matching advertisements based on keywords so that advertisements suitable for online contents are included in the corresponding contents.

A keyword-based advertisement matching method for online content according to a preferred embodiment of the present invention for solving the above problems includes generating content indexing data by performing indexing on online content; extracting one or more primary keywords from the indexing data; filtering negative image words from among the extracted main keywords; determining one or more commercial keywords related to key keywords from which words of the negative image are filtered out; and processing an advertisement corresponding to the determined commercial keyword to be included in the content.

Meanwhile, a keyword-based advertisement matching system for online content according to a preferred embodiment of the present invention for solving the above problems includes an indexing unit generating content indexing data by performing indexing on online content; And keyword extraction for extracting one or more main keywords from the indexing data, filtering words of a negative image among the extracted main keywords, and determining one or more commercial keywords related to the main keywords from which the words of the negative image are filtered. and processing so that an advertisement corresponding to the determined commercial keyword can be included in the content.

Meanwhile, the keyword-based advertisement matching method of online content may be implemented in a computer-readable recording medium on which a program to be executed by a computer is recorded.

The present invention indexes content to generate indexing data, extracts main keywords from the indexing data, summarizes syntax, and then creates a sitemap including the indexing data and keywords and provides them to search engines, so that users' content is searched for. There is an effect that can be exposed to the general public through search engines more efficiently.

In addition, the present invention provides a content sitemap to a search engine, and then periodically searches the search engine using keywords extracted from the content to check the search ranking, and the search ranking and the website that generated the corresponding content. By analyzing the access log of , it is possible to analyze the amount of traffic generated by each content and the advertising effect and profitability of each content, as well as the amount of traffic generated by each content producer, and the advertising effect and profitability.

According to another embodiment of the present invention, commercial keywords for advertisement matching are determined after filtering negative image words from among the main keywords extracted from the indexing data, so that advertisements associated with negative image words in the content are added to the content. By not including it, an advertisement suitable for the content can be exposed.

1 is a diagram showing the configuration of an online content value enhancement system using search engine optimization according to a preferred embodiment of the present invention.
2 is a flowchart illustrating a method for enhancing the value of online content using search engine optimization according to a preferred embodiment of the present invention.
3 is a diagram showing an example of indexing data generated by an indexing unit according to a preferred embodiment of the present invention.
4A and 4B are diagrams showing an example of a site map according to a preferred embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings.

1 is a diagram showing the configuration of an online content value enhancement system using search engine optimization (hereinafter, abbreviated as “online content value enhancement system”) according to a preferred embodiment of the present invention, and FIG. 2 is A flowchart illustrating a method for enhancing the value of online contents using search engine optimization (hereinafter, abbreviated as “method for enhancing the value of online contents”) according to a preferred embodiment of the present invention.

Referring to FIG. 1, the online content value enhancement system according to a preferred embodiment of the present invention includes an indexing unit 110, a keyword extraction unit 120, a site map generation unit 130, an indexing monitoring unit 140, and an analysis unit. Includes section 150.

Referring further to FIG. 2, the function of each component is described. First, the indexing unit 110 receives content from a plurality of websites (S210).

The plurality of websites are not limited as long as they can provide content through the Internet, such as general online shopping malls, media websites providing news articles, Internet portal sites, individual blog sites, and individual community websites.

In addition, the content may be content composed of only one of simple text, image, and video, or may include text and image, text and video, or both.

The indexing unit 110 performs indexing on the received content, generates content indexing data, and outputs it to the keyword extractor 120 (S220).

3 is a diagram showing an example of indexing data generated by the indexing unit 110 according to a preferred embodiment of the present invention. As shown in FIG. 3, the indexing data of the present invention includes various contents such as content title, content creation date, content author, content content, content posting URL, content posting website name or agency, and image and video metadata included in the content. contains one or more of the information.

The indexing data shown in Figure 3 includes the title of the content (Where are you going 'Dad' mothers, the reason why children are beautiful is because of their mother's genes), date (2013-02-25), author (Kookmin Ilbo Cookie News Team), content content (MBC entertainment program ~), URL (http://news.kukinews.com/article/view~), agency (Kookmin Ilbo), category (Entertainment), and keyword (Where are you going, Dad)?

The keyword extraction unit 120 extracts the main keywords from the indexing data input from the indexing unit 110, additionally extracts them as commercial keywords using the main keywords, and summarizes the contents of the main text, the main keywords, the commercial keywords and the body. The content summary is output to the site map generator 130 (S230).

The keyword extraction unit 120 extracts main keywords by accumulating scores by differentially assigning scores according to the following five conditions to each word extracted from the indexing data according to a morpheme analysis algorithm.

In the first condition, scores are given differently depending on whether the words are extracted from the title or the text. In general, words included in the title are more likely to be key keywords, so words extracted from the title are given a higher score than words extracted from the text.

In the second condition, when a word extracted from the title is found in the text or when a word extracted from the title is found in the text, a score is given to a word adjacent to the corresponding word. In this case, a higher score can be given in the case of the former.

[0028] For example, in the case of FIG. 3, in the article title ['Where are you going, Dad' mothers, the reason why children are beautiful is because of mother genes], the main keywords such as dad, where are you going, mom, child, gene, etc. have high scores. It is extracted as a given word. In addition, words adjacent to the main keywords extracted from the title are sequentially searched for in the article contents and scores are given. In the example of FIG. 3, explaining the process of finding words adjacent to the keyword “mom”, in the text [~ Recently, several photos were uploaded on an online community bulletin board under the title ‘Dad, where are the mothers’ beauty’~] , “mom”, which is a search target keyword, is found, and a predetermined number of adjacent words (eg, 2 words) before and after “mom” are searched for. In this case, the phrase "Dad, where are the mothers' beauty" is extracted, and here, "Dad" included in the two words before "Mom", "Where are you going", and "Mimo" included in the two words after "Mom" ”, “title” is extracted and given points.

The third condition gives a score differentially according to the position in the text where the word exists. Scores are differentially assigned depending on where the words are located in the body: introduction (less than the top 25% of the document size), body (more than 25% of the document size and less than 75% of the document size), and conclusion (more than the top 75% of the document size). grant In a preferred embodiment of the present invention, a higher score is given to a keyword located in the conclusion, but this can be adjusted according to the development method of the content. For example, in the case of a two-headed sentence, a higher score may be given to a word located in the introductory part.

The fourth condition assigns weights according to word frequency. Since frequently repeated words may be important words, a high score is given, but if the frequency exceeds a certain level relative to the total number of words, the corresponding content is rather likely to be a spam document, so a reverse weight is given.

The fifth condition is when there are three main keywords classified in advance as the main keywords of the category to which the corresponding content belongs, and the corresponding words exist, or in the same word as the main keywords of other previously analyzed documents of the same category on the same date. points are awarded for

When the main keyword is extracted from the text, the keyword extraction unit 120 additionally extracts commercial keywords using the extracted main keyword. The commercial keyword may be determined as a superordinate concept of the extracted main keyword or a word set in advance to be closely related, so that the content can be searched in the search process of the commercial keyword as well as the main keyword, and advertisements related to the commercial keyword to be included in the content.

For example, when main keywords such as “Lee Hyo-ri”, “sexy”, and “dance” are extracted as main keywords, the keyword extractor 120 may extract “diet” as a commercial keyword from the main keywords. In this case, the corresponding content may include advertisements for diet products, and may be exposed to users who search for diet as well as users who search for Hyori Lee, Sexy, and Dance.

In addition, when “Thailand” and “low-cost airline” are extracted as the main keywords, commercial keywords such as “travel” and “Thailand hotel” can be extracted in relation to this, but “Thailand” and “low-cost airline” as the main keywords. ” and “fall” are extracted together, it is possible to filter out the word “fall” of a negative image so that the corresponding content does not include an advertisement corresponding to a commercial keyword. Meanwhile, the sitemap generation unit 130 generates a sitemap using the indexing data input from the indexing unit 110, the main keyword input from the keyword extraction unit 120, and commercial keywords (S240), The sitemap is provided to a plurality of search engines (S250). 4A and 4B are diagrams showing an example of a site map according to a preferred embodiment of the present invention. FIG. 4A shows a site map for content provided by a general site, and FIG. 4B shows a site map for news content.

As shown in FIGS. 4A and 4B , the site map may include information such as link information of original image data and video data, news publishing organization, news publication date, major keywords, commercial keywords, etc. for use in search engines. there is. The site map itself may be created according to an internationally standardized format.

The indexing monitoring unit 140 receives notification from the sitemap generator 130 that a sitemap of specific content is provided to search engines, and the main keywords provided from the sitemap generator 130 or the keyword extractor 120. And, using commercial keywords, a search is performed in a plurality of search engines provided with a site map at regular time intervals to investigate the search ranking of content, and the search result is output to the analyzer 150 (S260).

The analysis unit 150 analyzes the search rank and the access log of the traffic induced on the website to analyze the advertisement effect for each traffic and the resulting profitability (S270).

For example, the analysis unit 150 may analyze traffic generation efficiency by analyzing the degree of traffic generation in comparison to the search ranking of the corresponding main keyword or commercial keyword included in the sitemap. In addition, the analyzer 150 analyzes each traffic access log to investigate whether or not each traffic accessed the corresponding website through which search engine, and after accessing, among a plurality of advertisements included in the corresponding content. It can be analyzed by examining whether or not which advertisement was selected.

In particular, in the advertisement analysis process, the analyzer 150 may analyze the location of the advertisement selected by the user (top advertisement, bottom advertisement, side advertisement, etc.), type of advertisement (batter advertisement, pop-up advertisement, etc.), etc. , it can be used to analyze the profitability of advertisements.

In addition, the analyzer 150 may not only analyze specific content, but also comprehensively analyze a plurality of content generated in the corresponding website.

In particular, the analyzer 150 analyzes the amount of traffic generated for each content and the advertising effect for each content for a plurality of content generated on the website, and analyzes what type of content has received public attention. It is possible to check the profit per content through the analysis of the profit per distributed content and reflect it in the budget required for producing the content (S280).

In addition, the analyzer 150 analyzes the amount of traffic generated by each producer (author) who produced the plurality of contents and the advertising effect for each content for the plurality of contents generated on the corresponding website, thereby determining the current status of revenue for each content producer. It is possible to compare and analyze the site's content production cost versus profit (S290).

In the online content value enhancement method described above with reference to FIG. 2, for convenience of description, steps S280 and S290 have been described as sequentially performed, but steps S280 and S290 are performed simultaneously or in reverse order. Of course, it can be performed as

The present invention can also be implemented as computer readable codes on a computer readable recording medium. A computer-readable recording medium includes all types of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. also includes In addition, the computer-readable recording medium is distributed in computer systems connected through a network, so that computer-readable codes can be stored and executed in a distributed manner.

So far, the present invention has been looked at with respect to its preferred embodiments. Those skilled in the art to which the present invention pertains will be able to understand that the present invention can be implemented in a modified form without departing from the essential characteristics of the present invention. Therefore, the disclosed embodiments should be considered from an illustrative rather than a limiting point of view. The scope of the present invention is shown in the claims rather than the foregoing description, and all differences within the equivalent scope will be construed as being included in the present invention.

110 indexing unit
120 keyword extraction unit
130 site map generator
140 indexing monitoring unit
150 analysis unit

Claims (1)

indexing online content to generate content indexing data;
extracting one or more primary keywords from the indexing data;
determining at least one word associated with the extracted main keywords as a commercial keyword among a plurality of words preset for advertisement matching;
generating a sitemap including the extracted main keywords and the determined commercial keyword and providing the sitemap to one or more search engines; and
When the extracted main keywords include words of a negative image, advertisements corresponding to the determined commercial keywords are not matched to the content, and when the extracted main keywords do not include words of a negative image, the determined commercial keywords are not matched. A keyword-based advertisement matching method for online content, comprising processing an advertisement corresponding to a keyword to be included in the content.

Images