KR100824435B1 - Method and apparatus of determining a listing rank of searched advertisement lists - Google Patents

Abstract

Disclosed is a method and apparatus for ranking a search advertisement list considering a related keyword related to an advertisement keyword which is a search input keyword. According to the present invention, a method of ranking a search advertisement list may further include considering a price bidd by advertisers for an advertisement keyword and an attribute value of an associated keyword associated with the advertisement keyword among keywords owned by the advertiser. And determining the exposure order of the list. As a result, even contents related to the search intention of the search user can be provided more abundantly by considering the related keyword for the keyword input to search.

Description

Method and apparatus of determining a listing rank of searched advertisement lists}

1 is a diagram illustrating an example of keywords that a portal operator sells to an advertiser and related keywords that are determined to be related to each other and grouped into a network;

FIG. 2 is a diagram illustrating an example of a keyword network composed of related keywords related to the keyword 'car'; FIG.

3 is a block diagram of a search unit according to a preferred embodiment of the present invention;

4 is a block diagram of a search advertisement list ranking apparatus according to a preferred embodiment of the present invention;

5 is a flowchart of a search advertisement list ranking method according to a preferred embodiment of the present invention.

The present invention relates to search advertisement list ranking, and more particularly, to a method and apparatus for ranking search advertisement list considering a related keyword related to an advertisement keyword which is a search input keyword.

In addition to the classic offline product sales, online product sales via the Internet are rapidly increasing. In order to sell a lot of products through the Internet, it is necessary to publicize their site to general users through active marketing methods such as advertising. Therefore, marketing strategies such as advertising on various portal sites are necessary.

On the other hand, portal sites that sell ads sell keywords for ads in order to increase advertising revenue, and when advertisers bid on these keywords, the advertisers with the highest bids are given priority. When consumers search using this keyword as a search term, they list the search results according to the advertiser's bid price ranking.

Therefore, from the advertiser's point of view, if you do not purchase all the keywords related to the product you want to sell, you will not be able to expose your ads to similar keywords. In addition, portal site operators have a problem that it is difficult to sell unpopular keywords.

Accordingly, a technical object of the present invention is to provide a search advertisement list ranking method and apparatus for determining an advertisement listing rank of an advertiser in consideration of not only the bid price of a search input keyword but also related keyword information. to be.

According to an aspect of the present invention, in the method of ranking a search advertisement list, the bid price of advertisers for an advertisement keyword and an attribute value of an associated keyword associated with the advertisement keyword among the keywords owned by the advertiser are further added. It is achieved by the search advertisement list ranking method, characterized in that to determine the advertisement list exposure ranking of the advertiser in consideration.

In addition, the technical problem is to obtain a degree of relevance of the advertising keywords of the relevant keywords bid by at least one advertiser among the related keywords of the advertising keyword, calculating the related score of the advertiser for the advertising keyword; Determining the exposure ranking of the advertisers' advertising list in consideration of the bid price of the advertisers and the calculated associated score for the advertising keyword and listing according to the exposure ranking ranking It is also achieved by the method.

On the other hand, according to another field of the present invention, the technical problem is to obtain the degree of association of the advertising keywords of the relevant keywords bid by at least one advertiser among the relevant keywords of the advertising keywords, the advertiser's association score for the advertising keywords Keyword association score calculation unit for calculating; And an exposure ranking unit determining an exposure ranking of the advertisers' advertisement list in consideration of the bid price of the advertisers for the advertisement keyword and the calculated related score. do.

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

FIG. 1 is a diagram illustrating an example of keywords that a portal business sells to an advertiser and related keywords that are determined to be related to each other and grouped into a network.

Portal operators present various keywords as shown in FIG. 1 to advertisers, and advertisers purchase keywords related to the products they want to sell, and then search their keywords to general consumers who perform searches with those keywords. Ads are listed in front of other advertisers' ads, requiring consumers to easily access them.

On the other hand, these keywords may be associated with each other keywords in a group (110). For example, related keywords related to 'cars' may be grouped into keywords such as 'car maintenance', 'used cars', 'sports cars', 'car supplies' and 'Ferrari' as a group. Also, as a related keyword group for 'sports', 'german', 'world cup' and 'soccer' may be grouped into one group.

FIG. 2 is a diagram illustrating an example of a keyword network composed of related keywords related to the keyword 'car'.

Referring to FIG. 2, keywords such as 'used cars', 'car tuning', 'car games', 'sports cars', 'car maintenance', and 'car supplies' exist under the representative keyword 'car' 200. Under the keyword 'used cars', there are keywords such as 'used cars for sale', 'used car quotes', etc., under the 'sports car' keyword, 'Ferrari', 'Lamborghini', 'Tuscany', 'imported sports car', 'Maibach' It can be seen that there are keywords such as 'car tuning'.

Such a keyword network can be made according to various methods, and how to implement the keyword network is irrelevant to the gist of the present invention.

3 is a block diagram of a search unit according to a preferred embodiment of the present invention.

The content information collecting unit 310 collects contents of various sites while navigating various web sites in order to provide various contents according to a search result to a user. The collected content is stored in the content information storage unit 320. The advertisement information may also be stored in the content information storage unit 320. The keyword network storage unit 330 stores information about keywords sold by a search site (portal site) that provides search results. That is, keyword network data composed of a keyword and an associated keyword as shown in FIG. 2 are stored. The keyword processing unit 340 reads the keyword network related to the keyword inputted by the user from the keyword network storage unit 330, and considers the related score of the related keyword and the bid price of the advertiser for the keyword entered as the search term. Determines the listing rank of the ads you want to expose.

That is, since there may be a plurality of advertisers bidding on one keyword, it is determined which advertisements of the advertisers are listed above in the advertisement list of the advertisers. The ranking of the listing is very important because the higher the ranking, the more likely users are to click to see its contents.

In addition, the search execution unit 350 reads the advertisements of the advertisers for the search word input by the user from the content information storage unit 320 and lists the advertisements according to the exposure order determined by the keyword processing unit 340 to provide the user.

4 is a block diagram of a search advertisement list ranking apparatus according to a preferred embodiment of the present invention.

The keyword data receiving unit 410 receives bidding information of advertisers for an advertisement keyword, which is a keyword input by a user, and keyword network data including related keywords related to the advertisement keyword.

The keyword association score calculation unit 420 obtains an association degree of the search input keywords of the related keywords bid by at least one advertiser among the related keywords of the keyword (ad keyword) inputted as the search word, and then determines the advertiser's response to the search input keyword. Calculate the association score. In other words, in a keyword network consisting of related keywords, which are keywords related to bid keywords, advertisers bid to extract relevant keywords that have obtained the right to display an advertisement, thereby obtaining a degree of association between the search input keyword and the extracted related keywords, and extracting the related associations. The correlation score is obtained by weighting the degree of correlation obtained with the keyword exposure ranking and the total number of advertisements for the associated keyword. Hereinafter, the calculation of the association score will be described in detail.

Table 1 below shows an example of the associated keywords and the degree of association constituting the 'car' keyword network shown in FIG.

Input keyword Related Keywords Association degree car Used Car 0.8 Used and Used Cars for Sale 0.5 Used Car / Used Car Price 0.4 Car tuning 0.3 Car games 0.3 Sports car 0.7 Sports Car / Ferrari 0.5 Sports Cars / Lamborghini 0.45 Sports Car / Tuscany 0.43 Sports Cars / Imported Sports Cars 0.59 Sports Cars / Maybach 0.33 Sports Car / Car Tuning 0.2 Car maintenance 0.6 Car accessories 0.65 bike 0.12

Suppose that A, B and C bid for the keyword 'car', and that A, B and C have related keywords related to 'car' as shown in Tables 2a to 2c, respectively. Here, the listing rank refers to the listing rank of A company in the number of lists printed when the corresponding keyword is entered.

A company Ownership Keywords Association degree Listing Rank Used Car 0.8 1/10 Car maintenance 0.6 5/10 bike 0.12 10/10

Company B Ownership Keywords Association degree Listing Rank Sports Car / Ferrari 0.5 1/10 Sports Cars / Imported Sports Cars 0.59 10/10

Company C Ownership Keywords Association degree Listing Rank none 0 none

Then, for example, the correlation score can be calculated as follows. Association score calculation may be in accordance with various methods and is not limited to this embodiment.

If the associated keyword associated with the search input keyword is Mp _i and the number of listing ads of the associated keyword is N _i and the listing rank of the associated keyword is o _i , the associated score may be calculated according to Equation 1 below. .

Next, the exposure ranking determiner 430 determines the list ranking of the advertisements that advertisers want to expose in consideration of the bid price of advertisers for the search input keyword and the related score calculated as described above. That is, the bid score is calculated by giving an appropriate weight to each advertiser's bid price for the search input keyword and the related scores calculated as described above, and the advertisers determine the ranking of the advertisement list according to the calculated bid scores.

More specifically, the listing score may be obtained as (Bid price x Bid price weight + Association score x Association score weight). For example, if the weight for a bid price of less than 1,000 won is 0.01 and the association score weight is 10, in the above example, the A, B, and C companies' ad ranks or impression positions may be calculated according to Table 3 below. have. The weight may be appropriately determined depending on whether the emphasis is on bid prices or whether there are many related keywords.

Company Name Bid price Association score Bid score Impression rank A 600 0.98 15.80 (600x0.01 + 0.98x10) One B 700 0.50 12.00 (700x0.01 + 0.50x10) 2 C 800 0.00 8.00 (800x0.01 + 0.00x10) 3

Referring to Table 3, it can be seen that Company A, which has the lowest bid price, is determined to be ranked first. That is, not only considering the bid price for the keyword, but because A company secures the most related keywords related to the keyword, the exposure ranking is increased in consideration of this point.

On the other hand, as described above, not only the association between keywords, but also the association between the keyword and the advertiser can be considered together. That is, it may be referred to whether the property of the advertiser, for example, a field related to a business.

For example, if the advertiser is a Samsung car, the keywords "car" and "SM5" are related, but they are not related to the keywords "sports car" and "Lamborghini," so these irrelevant keywords may not be considered in determining the impression rank. have. In other words, when considering how much related keywords are secured as described above, keywords not related to the advertiser may be excluded.

In addition, conventional methods for calculating similarity between keywords may also be used to calculate the degree of association between keywords, and the input frequency of a keyword input by a user may be considered. In taking input frequency into consideration, for example, a user who owns a frequently input keyword may be given a weight in calculating the degree of association.

5 is a flowchart of a search advertisement list ranking method according to a preferred embodiment of the present invention.

First, a search result of a user is received (S510). In other words, to find out which keyword the user has searched for, receive the search result for the keyword, and receive the search result for listing and showing the result according to the present invention. The step of receiving a search result is therefore not an essential component of the present invention.

Next, the keyword network data is received and an associated score is calculated (S520). That is, at least one of the related keywords of the searched input keyword (ad keyword) is obtained to obtain a degree of relevance of the search input keywords of the related keywords bid by the advertisers. To calculate the advertiser's association score for the keyword. More specifically, as described above, by extracting the relevant keywords bidding by advertisers in the keyword network consisting of related keywords that are keywords related to the advertising keywords, to obtain a degree of association between the advertising keywords and the extracted related keywords, the extracted association The correlation score is obtained by weighting the degree of correlation obtained with the keyword exposure ranking and the total number of advertisements for the associated keyword.

In addition, in consideration of the bid price of advertisers for the bidding advertisement keyword and the associated score calculated as described above, the advertiser determines the listing rank (exposure ranking) of the advertisement to be exposed (S530) and listings accordingly (S540). ).

That is, the bid score is calculated by giving a predetermined weight to each of the bid price of the advertiser and the calculated related scores for the ad keywords, and the advertiser's exposure rank is determined according to the calculated bid scores. List and display them.

According to the method of determining the search advertisement exposure ranking, the advertiser who owns a lot of related keywords is more likely to have more useful and diverse information to consumers, and thus, the exposure ranking is determined in consideration of this point.

On the other hand, the above-mentioned search advertisement list ranking method can be created by a computer program. Codes and code segments constituting the program can be easily inferred by a computer programmer in the art. In addition, the program is stored in a computer readable media, which is read and executed by a computer, thereby implementing a search advertisement list ranking method. The information storage medium includes a magnetic recording medium, an optical recording medium, and a carrier wave medium.

So far I looked at the center of the preferred embodiment for the present invention. Those skilled in the art will appreciate that the present invention can be implemented in a modified form without departing from the essential features of the present invention. Therefore, the disclosed embodiments should be considered in descriptive sense only and not for purposes of limitation. The scope of the present invention is shown in the claims rather than the foregoing description, and all differences within the scope will be construed as being included in the present invention.

As described above, according to the present invention, the following effects are obtained.

First, by considering related keywords for a keyword inputted to be searched, the content corresponding to the search intention of the search user can be more abundantly provided.

Second, by purchasing a related keyword together and advertising it, it is possible to advertise with a higher priority than when advertising with only individual keywords.

Third, the investment risk is lowered and marketing costs can be reduced by investing in related keywords rather than investing in every single keyword.

Fourth, it is possible to prevent listing manipulation due to illegal clicks of competitors.

Fifth, rather than unconditionally ranking the ad list according to the bid amount and listing it accordingly, by first listing the ad that best meets the search user's intention, the search user's profit can be maximized by inducing the search user's click. It is possible to reduce the disapproval of the search user for the advertisement.

Claims (10)

delete Calculating an association score of an advertiser with respect to the advertisement keyword by obtaining an association degree of the associated keywords bid by at least one advertiser among the associated keywords of the advertisement keyword; And Determining the exposure ranking of the advertiser's advertising list in consideration of the bid price of the advertiser and the calculated associated score for the advertising keyword and listing according to the exposure ranking, characterized in that it comprises the step of listing . The method of claim 2, wherein the calculating of the correlation score comprises: Extracts related keywords bid by the advertisers from a keyword network including related keywords which are keywords related to the advertisement keyword, to obtain a degree of association between the advertisement keyword and the extracted related keywords, and to display the exposure rank of the extracted related keywords And a correlation score obtained by weighting the obtained degree of association with the total number of advertisements associated with the associated keyword. The method of claim 2, wherein the listing step Bid scores are calculated by giving a predetermined weight to each of the bid price of the advertiser and the calculated related scores for the advertising keyword, and the exposure ranking of the advertisers' advertisement list is determined according to the calculated bid scores, according to the exposure rank. Search advertising list ranking method characterized in that the listing. The method of claim 2, The search advertisement list ranking method according to claim 1, wherein the related keywords are not related to the advertiser, in consideration of the relation between the attributes of the advertiser and the related keywords when calculating the related score. A keyword association score calculation unit configured to obtain an association degree of the associated keywords bid by at least one advertiser among the related keywords of the advertisement keyword, and calculate an association score of the advertiser with respect to the advertisement keyword; And And an exposure ranking determiner configured to determine an exposure ranking of the advertisers' advertisement list in consideration of the bid price of the advertisers for the advertisement keyword and the calculated related score. The method of claim 6, And a keyword data receiver configured to receive keyword network data including bid information of advertisers for the advertisement keyword and related keywords related to the advertisement keyword. The method of claim 6 or 7, wherein the keyword association score calculation unit Extracts related keywords bid by the advertisers from a keyword network including related keywords which are keywords related to the advertisement keyword, to obtain a degree of association between the advertisement keyword and the extracted related keywords, and to display the exposure rank of the extracted related keywords And an associated score obtained by weighting the obtained degree of association with the total number of advertisements associated with the associated keyword. The method of claim 6 or 7, wherein the exposure ranking unit A search advertisement is calculated by giving a predetermined weight to each of the bid price of the advertiser and the calculated related score for the advertisement keyword, and determining the advertisement list exposure ranking of the advertiser according to the calculated bid score. List ranking device. A computer-readable recording medium having recorded thereon a program for executing the method of claim 2 on a computer.

Images