KR20170095492A - Method AND SYSTEM for Selecting A related keyword Group of Blog Marketing Based on Keyword - Google Patents
Method AND SYSTEM for Selecting A related keyword Group of Blog Marketing Based on Keyword Download PDFInfo
- Publication number
- KR20170095492A KR20170095492A KR1020160016921A KR20160016921A KR20170095492A KR 20170095492 A KR20170095492 A KR 20170095492A KR 1020160016921 A KR1020160016921 A KR 1020160016921A KR 20160016921 A KR20160016921 A KR 20160016921A KR 20170095492 A KR20170095492 A KR 20170095492A
- Authority
- KR
- South Korea
- Prior art keywords
- keyword
- quot
- frequency
- document
- idf
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000002860 competitive effect Effects 0.000 claims description 37
- 238000004364 calculation method Methods 0.000 claims description 23
- 238000010187 selection method Methods 0.000 claims description 11
- 230000000877 morphologic effect Effects 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 8
- 238000000605 extraction Methods 0.000 description 4
- 230000007774 longterm Effects 0.000 description 3
- 238000010845 search algorithm Methods 0.000 description 3
- 241000086550 Dinosauria Species 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 206010044565 Tremor Diseases 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
-
- G06F17/2755—
-
- G06F17/30864—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
-
- G06Q50/30—
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Computing Systems (AREA)
- Operations Research (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Description
The present invention relates to keyword selection for keyword-based blog marketing, and more particularly, to a related keyword selection method and a selection system for keyword-based blog marketing, and a competitive power calculation method and a calculation system of the related keyword.
Recently, the influence of SNS (Social Network Service) and online media is rising along with the spread of smartphones.
In particular, blogs based on keyword search portal are used not only as social network functions but also as a source of information and marketing means of companies, beyond simple personal information records.
According to the analysis of the impact of blog marketing, blogs are analyzed to analyze the fact that blogs have a larger ripple effect than comparatively low cost and give a priesthood to consumers. As a result of surveying the most effective services of digital marketing, blogs ranked first (34%).
One of the main reasons for the high influence of blogs is that blog information is exposed to the top in the search results of portal sites. This is the result of proving the informativeness of the blog. Naver, the largest portal site in Korea, provides a keyword-based search service, which uses a blog search system to expose highly relevant blogs as search results.
As the utilization of blog marketing increases, efforts are being made to analyze the blog search system of a large portal site and to be exposed at the top of keyword search keyword search. Recently, large corporations are developing strategies to promote their products by utilizing large amounts of influential blog information in portal search results.
The cost of marketing is further increased in order to make the top exposure of the portal site search result of the competitive keyword. Even if the keywords are paid for at a high cost and temporarily exposed to competitive keywords, the search results of popular keywords will be changed frequently due to the preference of the latest information, so it is difficult to expect a long-term marketing effect.
For reference, Korean Patent Registration No. 10-0751560 entitled " Keyword Advertisement Analysis System "proposes a system that presents optimized keywords in terms of cost.
On the other hand, some companies, such as SMEs and small merchants, are trying to run their own blogs, reduce marketing costs, and provide information on products. However, since there are about 10 million blogs currently in operation, it is difficult to expose relevant information to keyword search results on portal sites.
For top exposure, the value of the blog itself, as well as its relevance to the keyword, affects keyword search results. This is called the blog index, which usually requires at least a few months of long-term, regular effort to get a high blog index. Even if you have a high blog index, it is difficult to actively cope with search results that fluctuate from day to day in the case of highly competitive keywords.
On the other hand, the search volume of the keyword and the number of the blogs included in the search result of the keyword are not always proportional. One of the basic purposes of the blog is the personal record, and the keyword search purpose and the blog operation purpose always meet It is because there is not.
Blog (blog), a compound word of Web (Web) and Log (Journal), refers to a journal recorded by an individual on the Web. The number of domestic operating blogs is estimated to be about 10 million, which was used mainly for the purpose of establishing personal records or social networks in the past.
A large portal site also acknowledges the informativeness of blogs and exposes them to search results. As a result, blogs are becoming popular with introduction to products and services of companies, and marketing strategies in the form of late reviews. The information of ZyLog showed higher reliability and delivery power than other digital marketing.
Web search algorithms have been proposed using various methods for evaluating the importance of web documents and determining rankings. Among them, the PageRank algorithm applied to the Google search engine proposes a method of calculating the weight through hyperlinks between documents and is used as the basic theory of most search engines at present.
However, due to the nature of blogs, the frequency of use of hyperlinks is significantly lower than that of ordinary web pages, and the web search algorithm is not suitable for blog search. Thus, a blog ranking algorithm considering the features of blogs has been proposed. The blog ranking algorithm based on PageRank algorithm analyzed similarity and connectivity between blogs instead of hyperlinks.
Also, the B2Rank algorithm considers the frequency of blogging and the number of comments, and the EigenRumor algorithm applies the attractiveness of the blog and the user 's evaluation numerically. In addition, a method to determine blog ranking by numerical scrapping, trackback, etc. Has been proposed. Most blog search algorithms are configured to analyze the relevance of the value of the blog itself and the search keyword.
Therefore, for the top exposure in blog search, active long-term effort is required for the value of the blog itself as well as its relevance to the keyword.
SUMMARY OF THE INVENTION The present invention has been proposed in order to solve the above technical problems, and provides a method and a system for selecting related keywords for keyword-based blog marketing.
Also, it provides a method and system for calculating the competitiveness of related keywords for keyword based blog marketing.
According to an embodiment of the present invention, there is provided a method of selecting an associated keyword for keyword-based blog marketing, the method comprising: collecting search results of a portal site for a target keyword; Extracting a word of the word; According as the given keyword weight for a selected one of a plurality of word extraction associated keywords (ω i), normalized keywords for the usage count of the document (D) all keywords used many times over a selected related keywords (ω i) of (ω j) in the Of the related keyword (? I ) based on the difference value between the number N of the entire documents D and the number n of the documents D containing the selected related keywords? I , And a calculation step of calculating an inverse number (IDF) of the document frequency indicating the sparseness and calculating an inverse number (IDF) of the normalized keyword frequency (TF) and a document frequency to calculate a related keyword weight value (IF-IDF) A selection method is provided.
The related keyword weight value (IF-IDF) is calculated by multiplying the normalized keyword frequency (TF) by the inverse number (IDF) of the document frequency.
The normalized keyword frequency (TF) is defined by the following equation (1).
&Quot; (1) "
freq (ω i , D): the frequency of use of a particular word (ω i ) in the document (D)
The inverse number (IDF) of the document frequency is defined by the following equation (2).
&Quot; (2) "
The associated keyword weight value (IF-IDF) is defined as Equation (3).
&Quot; (3) "
According to another embodiment of the present invention, there is provided a related keyword selection system for keyword-based blog marketing, which collects search results of a portal site for a target keyword, A word extracting unit for extracting a plurality of displayed words; And a selected one of a plurality of word extraction associated keyword weighting unit whether to grant the keyword weight of (ω i); including, wherein the weighting unit includes a document (D) all keywords (ω j) used many times over a selected associations in The normalized keyword frequency TF for the use frequency of the keyword ω i is calculated and the number n of the documents D containing the number N of the entire documents D and the selected related keywords ω i , IDF of the document frequency indicating the scarcity of the related keyword ω i is calculated based on the difference value between the normalized keyword frequency TF and the document frequency IDF to calculate the associated keyword weight IF- ) Is calculated based on the keyword information.
Further, according to another embodiment of the invention, the associated keywords (ω i) Monthly searches (AS (ω i)) is proportional and associated keywords blog number (NB (ω i) containing the (ω i) of the ) in inverse proportion, and, associated with the keyword (mean creation date of containing the ω i) blog to the difference value (ADB (ω i of the current date) for calculating a) competitive value of the associated keyword (CV (ω i) proportional to) the A method for calculating the competitiveness of an associated keyword, comprising:
Further, the competitive value CV (? I ) of the associated keyword is defined as Equation (4).
&Quot; (4) "
Further, according to another embodiment of the invention, the associated keywords (ω i) Monthly searches (AS (ω i)) is proportional and associated keywords blog number (NB (ω i) containing the (ω i) of the ) in inverse proportion, and, associated with the keyword (mean creation date of containing the ω i) blog to the difference value (ADB (ω i of the current date) for calculating a) competitive value of the associated keyword (CV (ω i) proportional to) the And a competitiveness calculating unit.
According to the related keyword selection method and the selection system for keyword-based blog marketing according to the embodiment of the present invention and the competitive power calculation method and the calculation system of the related keyword, efficient keyword can be selected considering the search volume and the possibility of high exposure have.
In addition, it is possible to extract related keywords having high relevance to the required target keywords, analyze the search volume and competitiveness of each keyword, and recommend the most efficient related keywords.
Also, when blogging for marketing, you can select keywords that are similar to your target keywords, so you can recommend keywords that are competitive and appealing to the top exposure.
1 is a diagram illustrating a related keyword selection method according to an embodiment of the present invention;
2 is a block diagram of a related keyword selection system according to an embodiment of the present invention.
3 is a diagram illustrating a competitive power calculation method of a related keyword according to an embodiment of the present invention;
FIG. 4 is a block diagram of a competitive power calculation system for a related keyword according to an embodiment of the present invention.
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, in order to facilitate a person skilled in the art to easily carry out the technical idea of the present invention.
1 is a diagram illustrating a related keyword selection method according to an embodiment of the present invention.
The related keyword selection method (1) according to the present embodiment includes only a brief configuration for clearly explaining the technical idea to be proposed.
Referring to FIG. 1, the related keyword selection method (1) includes a word extraction step (S10) and a weight calculation step (S20).
In other words, in the related keyword selection method for keyword-based blog marketing (1)
First, a step of collecting search results of a portal site for a target keyword and extracting a plurality of words displayed on the collected document D through a Korean morphological analysis is performed. - S10 -
Next, in assigning the keyword weight of the selected related keyword (? I ) among the plurality of extracted words,
Calculates a normalized keyword frequency (TF) with respect to the number of times of use of the associated keyword (? I ) selected from the number of times of use of all the keywords (? J ) in the document (D)
The whole document (D) the number (N) and the selected associated keywords inverse of the document frequency indicating the rarity of keywords (ω i) associated on the basis of the difference value of the number (n) of the document (D) including the (ω i) of ( IDF)
A calculation step of calculating the associated keyword weight value IF-IDF by calculating the normalized keyword frequency TF and the inverse number IDF of the document frequency is performed. - S20 -
At this time, the associated keyword weighting value (IF-IDF) can be calculated by multiplying the normalized keyword frequency (TF) by the inverse number (IDF) of the document frequency.
The normalized keyword frequency (TF) can be defined by the following equation (1).
&Quot; (1) "
In addition, the inverse number (IDF) of the document frequency can be defined by the following equation (2).
&Quot; (2) "
That is, for the related keyword extraction, the document contents of the portal site keyword search result are collected, and the nouns used are extracted through the morphological analysis of Hangeul. The extracted noun words are used to calculate the frequency to determine the importance.
The related keyword weight (IF-IDF) is used as a weight calculation method for determining importance.
First, the normalized keyword frequency (TF) calculates the weight of a specific word (? I ) in the document (D) through the frequency (freq (? I , D)). However, since the frequency of the document increases as the content of the document increases, the normalized keyword frequency (TF), which is obtained by dividing the frequency by the total number of words, can be used.
&Quot; (1) "
Next, the Inverse Document Frequency (IDF) calculates the scarcity and informationality of a word using the document frequency inverse number. If the total number of documents in the blog search result is N and the number of documents containing a specific word (? I ) is n, the inverse number (IDF) of the document frequency can be obtained as follows.
&Quot; (2) "
Next, the associated keyword weighting value (IF-IDF) can be obtained as follows by calculation of the normalized keyword frequency (TF) and the inverse number of the document frequency (IDF).
&Quot; (3) "
2 is a configuration diagram of an associated
Referring to FIG. 2, the related
In other words, in the related keyword selection system for keyword-based blog marketing (2)
The
In addition, the
In particular, the
Calculates a normalized keyword frequency (TF) with respect to the number of times of use of the associated keyword (? I ) selected from the number of times of use of all the keywords (? J ) in the document (D)
The whole document (D) the number (N) and the selected associated keywords inverse of the document frequency indicating the rarity of keywords (ω i) associated on the basis of the difference value of the number (n) of the document (D) including the (ω i) of ( IDF)
The related keyword weight value IF-IDF is calculated by calculating the normalized keyword frequency TF and the inverse number IDF of the document frequency.
As described above, the related keyword weight value IF-IDF can be calculated by multiplying the normalized keyword frequency TF by the inverse number IDF of the document frequency.
The normalized keyword frequency (TF) can be defined by the following equation (1).
&Quot; (1) "
In addition, the inverse number (IDF) of the document frequency can be defined by the following equation (2).
&Quot; (2) "
To extract related keywords, document contents of portal site keyword search results are collected and nouns are extracted through morphological analysis of Hangul. The extracted noun words are used to calculate the frequency to determine the importance.
The related keyword weight (IF-IDF) is used as a weight calculation method for determining importance.
First, the normalized keyword frequency (TF) calculates the weight of a specific word (? I ) in the document (D) through the frequency (freq (? I , D)). However, since the frequency of the document increases as the content of the document increases, the normalized keyword frequency (TF), which is obtained by dividing the frequency by the total number of words, can be used.
&Quot; (1) "
Next, the Inverse Document Frequency (IDF) calculates the scarcity and informationality of a word using the document frequency inverse number. If the total number of documents in the blog search result is N and the number of documents containing a specific word (? I ) is n, the inverse number (IDF) of the document frequency can be obtained as follows.
&Quot; (2) "
Next, the associated keyword weighting value (IF-IDF) can be obtained as follows by calculation of the normalized keyword frequency (TF) and the inverse number of the document frequency (IDF).
&Quot; (3) "
On the other hand, the competitiveness of the associated keyword (? I ) can be calculated after the related keyword (? I ) is selected through the above-described method.
FIG. 3 is a diagram illustrating a competitive power calculation method of a related keyword according to an embodiment of the present invention.
Referring to FIG. 3, the competitive power calculation method (3) of the related keyword includes a step (S30) of selecting a related keyword (? I ) and a step (S40) of calculating a competitive power value.
That is, in the competitive power calculation method (3) of the selected related keyword (? I )
Step (S30) for selecting the priority, associated keywords (ω i) may be selected for the associated keywords (ω i) by the method and system of the above-described FIGS. - S30 -
Next, in proportion to the monthly retrieval amount AS (? I ) of the related keyword? I ,
Is inversely proportional to the number of blogs NB (? I ) including the related keyword? I ,
An association step for calculating a keyword (ω i) competitive value of the associated keyword that is proportional to the difference (ADB (ω i)) of the average creation date and the current date of the blog contains (CV (ω i)) are in progress. - S40 -
The competitive value CV (? I ) of the associated keyword can be defined as shown in Equation (4) below.
&Quot; (4) "
4 is a configuration diagram of a competitive
Referring to FIG. 4, the
First, the associated
Next, the
Is inversely proportional to the number of blogs NB (? I ) including the related keyword? I ,
Associated calculates the keyword (ω i) competitive value of the associated keyword that is proportional to the difference (ADB (ω i)) of the average creation date and the current date of the blog contains (CV (ω i)).
The competitive value CV (? I ) of the associated keyword can be defined as shown in Equation (4) below.
&Quot; (4) "
Certain associated keyword competitiveness (CV (ω i)) for the measurement and monthly search volume (AS (ω i)) and blog number (NB (ω i)), and higher exposure to
The related keywords (ω i ) are recommended in reverse order of the calculated competitiveness values.
As the monthly search volume (AS (ω i )) is higher, the marketing blog is more frequently exposed, so it is advantageous for the competitive value (CV (ω i )) and the smaller the blog number (NB (ω i ) It is highly competitive because it is advantageous for the top exposure of blog.
The monthly search volume is associated with the total number of exposures, which can be compensated by using multiple keywords with a small search volume. However, as the number of blogs included in the searched keywords increases, the number of top exposures rapidly deteriorates. Therefore, it is necessary to be treated as an important factor as compared with the monthly searched amount because the number of keywords in the blog can not be solved.
The higher the difference value ADB (? I ) between the average creation date and the current date of the top exposure block of the keyword is advantageous to the competitive value CV (? I ). The keywords of frequently created blogs are disadvantageous to competitiveness because they are frequently replaced even if the exposure is high. The fact that the blogs created in the past are the top exposures can be attributed to the number of blogging or the number of blogging using the keywords, which is advantageous for competitiveness.
Tables 1 through 5 illustrate related groups of keywords for loans, marriages, moving, toys, travel, and their competitiveness through the methods and systems described above.
Referring to Table 1, it can be seen that the related keywords (ω i ) for the target keyword "loan" have high competitiveness in the order of feed, loan, guarantor, high interest rate, repayment, and interest rate.
Referring to Table 2, it can be seen that the related keywords (ω i ) for the target keyword "marriage" are highly competitive in order of wedding invitation, coupling, robes, gifts, compatibility, wedding ceremony, dress, and priest.
Referring to Table 3, it can be confirmed that the related keywords (ω i ) for the "target" keyword "moving" have a high competitive power in the order of drag, one room, and quote.
Referring to Table 4, it can be confirmed that the related keyword (ω i ) for the target keyword "toy" has a high competitive power in the order of turning, toy, dinosaur, infant, and robot.
Referring to Table 5, it can be seen that the related keywords (ω i ) for the target keyword "travel" are highly competitive in the order of Jeju Island, autumn, package, sea, hotel, airport, and newlywed.
In the embodiment of the present invention, in order to retrieve the related keywords, morphological analysis is performed on the contents of 100 documents of the top blog, and the degree of association is calculated based on the frequency of the keywords of the nouns or compound nouns.
According to the related keyword selection method and the selection system for keyword-based blog marketing according to the embodiment of the present invention and the competitive power calculation method and the calculation system of the related keyword, efficient keyword can be selected considering the search volume and the possibility of high exposure have.
In addition, it is possible to extract related keywords having high relevance to the required target keywords, analyze the search volume and competitiveness of each keyword, and recommend the most efficient related keywords.
Also, when blogging for marketing, you can select keywords that are similar to your target keywords, so you can recommend keywords that are competitive and appealing to the top exposure.
Thus, those skilled in the art will appreciate that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. It is therefore to be understood that the embodiments described above are to be considered in all respects only as illustrative and not restrictive. The scope of the present invention is defined by the appended claims rather than the detailed description and all changes or modifications derived from the meaning and scope of the claims and their equivalents are to be construed as being included within the scope of the present invention do.
10: word extracting unit
20: Weight assignment
30: Associative keyword selection unit
40: Competitiveness Calculator
Claims (14)
Collecting search results of a portal site for a target keyword, and extracting a plurality of words displayed on the collected document (D) through a Korean morphological analysis;
In assigning the keyword weight of the selected related keyword (? I ) among the plurality of extracted words,
Calculates a normalized keyword frequency (TF) with respect to the number of times of use of the associated keyword (? I ) selected from the number of times of use of all the keywords (? J ) in the document (D)
The whole document (D) the number (N) and the selected associated keywords inverse of the document frequency indicating the rarity of keywords (ω i) associated on the basis of the difference value of the number (n) of the document (D) including the (ω i) of ( IDF)
A calculation step of calculating an associated keyword weight value IF-IDF by calculating a normalized keyword frequency (TF) and an inverse number of a document frequency (IDF);
The method comprising:
Wherein the related keyword weighting value (IF-IDF) is calculated by multiplying a normalized keyword frequency (TF) by an inverse number (IDF) of the document frequency.
Wherein the normalized keyword frequency (TF) is defined as: " (1) "
&Quot; (1) "
freq (ω i , D): the frequency of use of a particular word (ω i ) in the document (D)
Wherein the inverse number (IDF) of the document frequency is defined by the following equation (2).
&Quot; (2) "
Wherein the related keyword weighting value (IF-IDF) is defined as Equation (3).
&Quot; (3) "
A word extracting unit for collecting search results of a portal site for a target keyword and extracting a plurality of words displayed in the collected document D through a Korean morphological analysis; And
And a weight assigning unit for assigning a keyword weight of the selected related keyword (? I ) among the plurality of extracted words,
The weighting unit may include:
Calculates a normalized keyword frequency (TF) with respect to the number of times of use of the associated keyword (? I ) selected from the number of times of use of all the keywords (? J ) in the document (D)
The whole document (D) the number (N) and the selected associated keywords inverse of the document frequency indicating the rarity of keywords (ω i) associated on the basis of the difference value of the number (n) of the document (D) including the (ω i) of ( IDF)
Wherein the related keyword weighting unit (IF-IDF) is calculated by calculating the normalized keyword frequency (TF) and the inverse number of the document frequency (IDF).
Wherein the related keyword weighting value (IF-IDF) is calculated by multiplying a normalized keyword frequency (TF) by an inverse number (IDF) of a document frequency.
Wherein the normalized keyword frequency (TF) is defined as: " (1) "
&Quot; (1) "
freq (ω i , D): the frequency of use of a particular word (ω i ) in the document (D)
Wherein the inverse number of the document frequency (IDF) is defined by the following equation (2).
&Quot; (2) "
Wherein the related keyword weighting value (IF-IDF) is defined as Equation (3).
&Quot; (3) "
Relative to the associated keyword monthly search volume (AS (ω i)) of (ω i), and
Is inversely proportional to the number of blogs NB (? I ) including the related keyword? I ,
Association step for calculating a keyword (ω i) competitive value of the associated keyword that is proportional to the average difference value and the creation date (ADB (ω i)) for the current day of the blog that contains (CV (ω i));
The method comprising the steps of:
Wherein the competitive value CV (? I ) of the associated keyword is defined as Equation (4).
&Quot; (4) "
Relative to the associated keyword monthly search volume (AS (ω i)) of (ω i), and
Is inversely proportional to the number of blogs NB (? I ) including the related keyword? I ,
Associate keywords mean the creation date of the blog that contains the (ω i) and the calculated competitive for calculating the value of the associated competitive keyword that is proportional to the difference (ADB (ω i)) for the current day (CV (ω i)) section;
Wherein the system further comprises:
Wherein the competitive value CV (? I ) of the associated keyword is defined as Equation (4).
&Quot; (4) "
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020160016921A KR101791418B1 (en) | 2016-02-15 | 2016-02-15 | Method AND SYSTEM for Selecting A related keyword Group of Blog Marketing Based on Keyword |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020160016921A KR101791418B1 (en) | 2016-02-15 | 2016-02-15 | Method AND SYSTEM for Selecting A related keyword Group of Blog Marketing Based on Keyword |
Publications (2)
Publication Number | Publication Date |
---|---|
KR20170095492A true KR20170095492A (en) | 2017-08-23 |
KR101791418B1 KR101791418B1 (en) | 2017-10-31 |
Family
ID=59759520
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020160016921A KR101791418B1 (en) | 2016-02-15 | 2016-02-15 | Method AND SYSTEM for Selecting A related keyword Group of Blog Marketing Based on Keyword |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR101791418B1 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20190085243A (en) * | 2018-01-10 | 2019-07-18 | 주식회사 메디씨앤씨 | Method for selecting target user group and computer system performing the same |
KR20220117425A (en) * | 2021-02-17 | 2022-08-24 | 김현준 | Marketability analysis and commercialization methodology analysis system using big data |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100863990B1 (en) * | 2006-11-28 | 2008-10-16 | 주식회사 오피엠에스 | Advertising System and method using category |
KR100892848B1 (en) * | 2007-05-31 | 2009-04-10 | 엔에이치엔(주) | Product automatic setting method and system thereof |
-
2016
- 2016-02-15 KR KR1020160016921A patent/KR101791418B1/en active IP Right Grant
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20190085243A (en) * | 2018-01-10 | 2019-07-18 | 주식회사 메디씨앤씨 | Method for selecting target user group and computer system performing the same |
KR20220117425A (en) * | 2021-02-17 | 2022-08-24 | 김현준 | Marketability analysis and commercialization methodology analysis system using big data |
Also Published As
Publication number | Publication date |
---|---|
KR101791418B1 (en) | 2017-10-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Cheng et al. | Personalized click prediction in sponsored search | |
US8909652B2 (en) | Determining entity popularity using search queries | |
CN109190043A (en) | Recommended method and device, storage medium, electronic equipment and recommender system | |
Yu | The dynamic competitive recommendation algorithm in social network services | |
CN102629257B (en) | Commodity recommending method of e-commerce website based on keywords | |
CN103455487B (en) | The extracting method and device of a kind of search term | |
US20120254152A1 (en) | Optimization of social media engagement | |
CN104866554B (en) | A kind of individuation search method and system based on socialization mark | |
CN102841946A (en) | Commodity data retrieval sequencing and commodity recommendation method and system | |
Hasan et al. | Query suggestion for e-commerce sites | |
Zhang et al. | Bid keyword suggestion in sponsored search based on competitiveness and relevance | |
KR100744063B1 (en) | Internet search advertising service system and method thereof | |
US10127322B2 (en) | Efficient retrieval of fresh internet content | |
KR20160089177A (en) | Polarity-based user opinion ranking algorithm and system | |
TW201426357A (en) | Method and apparatus of ordering search data, and data search method and apparatus | |
Hu et al. | A POI-sensitive knowledge graph based service recommendation method | |
Wu et al. | Keyword extraction for contextual advertisement | |
US8498979B1 (en) | System and method for semantic analysis of social network user activities | |
CN104036008A (en) | Keyword competitiveness analyzing method and device | |
KR101791418B1 (en) | Method AND SYSTEM for Selecting A related keyword Group of Blog Marketing Based on Keyword | |
WO2020057237A1 (en) | Influence detection method applicable to object of interest, and electronic terminal and storage medium | |
CN107085573B (en) | Hotspot information acquisition method and device | |
Tsai | A fuzzy-based personalized recommender system for local businesses | |
Hasegawa et al. | Trip tweets search by considering spatio-temporal continuity of user behavior | |
CN107688979A (en) | Method and apparatus for providing credit reference information |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A201 | Request for examination | ||
E902 | Notification of reason for refusal | ||
E902 | Notification of reason for refusal | ||
E701 | Decision to grant or registration of patent right | ||
GRNT | Written decision to grant |