Method and system of inspecting advertisement through keyword comparison

• US 8,793,158 B2
• Filed: 04/30/2008
• Issued: 07/29/2014
• Est. Priority Date: 05/04/2007
• Status: Active Grant

• Current Assignee: Naver Corporation
• Original Assignee: NHN Business Platform Corp. (Naver Corporation)
• Inventors: Wee, Wu Sic, Kim, Minuk, Roh, Hye Jung
• Primary Examiner(s): Kazimi, Hani M
• Assistant Examiner(s): Ali, Hatem M
• Application Number:
  US12/113,182
• Publication Number:
  US 20080275783A1
• Time in Patent Office: 2,281 Days
• Field of Search: 705/14
• US Class Current: 705/14.2
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 30/0277 Online advertisement

Abstract

A method and system of inspecting advertising contents of a keyword advertisement is provided. The method includes: crawling a Universal Resource Locator (URL) registered by an advertiser and extracting a URL keyword related to an advertisement site of the advertiser; extracting a target keyword from a plurality of advertisement information being registered in relation to the URL; and determining further inspection-required advertisement information through keyword comparison between the extracted URL keyword and the target keyword, the further inspection-required advertisement information having low relevance to the advertisement site.

Claims

1. A computer-implemented method, the method comprising:

receiving advertisement information associated with a website of an advertiser for advertising, the advertisement information comprising a Universal Resource Locator (URL), one or more advertising keywords, and advertising content to be displayed for the advertising;

collecting one or more web pages by crawling the URL, wherein a URL keyword is extracted from contents of the collected web pages;

extracting a target keyword from the advertisement information associated with the website, wherein the target keyword comprises the advertising keywords that are registered by the advertiser;

determining, by a processor of the computer, a relevance score by using keyword comparison of the target keyword with respect to the URL keyword, the relevance score being determined based on at least one of frequency of occurrence of a plurality of query sets by considering a first query and a second query as a query set, the second query being entered after the first query is entered, word statistics information obtained through words included in document sets existing on webs, documents, word classification with respect to the words or document classification with respect to the documents, and related search word sets being extracted from a related search word database provided by an Internet portal site; and

determining, by the processor of the computer, an inspection index of each of the advertisement information, the inspection index being an indication of whether an inspection is required for the advertisement information according to the relevance score between the URL keyword and the target keyword.

2. The method of claim 1, wherein crawling the URL comprises:

crawling at least one website associated with the URL; and

extracting the URL keyword from contents of a web page linked by the URL.

3. The method of claim 1, wherein the advertising content comprises a title and a description of a website associated with the URL, the advertising content being displayed for the advertising.

4. The method of claim 1, wherein the one or more advertising keywords and the advertising content to be displayed are selected by the advertiser.

5. The method of claim 1, wherein determining the relevance score between the URL keyword and the target keyword comprises:

indexing a relevance between the URL keyword and the target keyword associated with the advertising; and

evaluating the value of the relevance based upon the index.

6. The method of claim 5, wherein indexing the relevance comprises:

indexing the relevance associated with the advertising based upon the relevance score of the target keyword.

7. The method of claim 6, wherein indexing the relevance further comprises:

matching each of the advertisement information to the relevance score of the target keyword extracted from the advertisement information;

calculating an average value of the relevance score and matching the average value to each of the plurality of advertisement information; and

determining the average value of the relevance score to be the value of a relationship between the at least one URL keyword and the at least one target keyword.

8. The method of claim 6, further comprising:

listing at least one target keyword based on the relevance score; and

displaying the listed target keyword.

9. The method of claim 5, further comprising:

listing the target keyword extracted from the advertisement information based on the indexed relevance; and

displaying the listed advertisement information.

10. The method of claim 1, further comprising:

checking the target keyword based on the relevance score and whether an attention-required keyword associated with an inspection exists; and

determining whether the attention-required keyword is extracted and whether the inspection-required advertisement information is further inspected.

11. A method using a processor for inspecting an advertisement, the method comprising:

receiving advertisement information associated with at least one website of an advertiser for advertising, the advertisement information comprising a Universal Resource Locator (URL), at least one advertising keyword, and advertising contents to be displayed for the advertising;

extracting at least one keyword associated with a buzzword related to a social issue from at least one web page;

extracting one or more web pages by crawling the URL, wherein a URL keyword is extracted from contents of the collected web pages;

extracting at least one target keyword extracted from the advertisement information associated with the at least one web site, wherein the target keyword is registered by the advertiser;

determining, by the processor, a relevance relationship between the keyword associated with the buzzword and the target keyword in accordance with a rule, wherein the relevance relationship is determined based on at least one of frequency of occurrence of a plurality of query sets by considering a first query and a second query as a query set, the second query being entered after the first query is entered, word statistics information obtained through words included in document sets existing on webs, documents, word classification with respect to the words or document classification with respect to the documents, and related search word sets being extracted from a related search word database provided by an Internet portal site; and

determining, by the processor, an index of each of the advertisement information, the index being an indication of whether an inspection is required for the advertisement information according to the relevance relationship between the URL keyword and the keyword associated with the buzzword.

12. The method of claim 11, wherein at least one web page comprises at least one online news article page and a real-time issue keyword page.

13. The method of claim 11, wherein the advertising contents comprise a title and a description of at least one of the website associated with the URL, the advertising contents being displayed for the advertising.

14. The method of claim 11, further comprising:

displaying the target keyword to determine whether an inspection is required.

15. The method of claim 11, wherein determining the relevance relationship comprises:

searching for a target keyword related to the extracted keyword associated with the buzzword.

16. One or more non-transitory computer-readable storage media comprising a computer-executable program, which when executed by one or more processors, performs:

receiving advertisement information associated with a website of an advertiser for advertising, the advertisement information comprising a Universal Resource Locator (URL), at least one first keyword, and advertising content to be displayed for the advertising;

collecting information by crawling the website associated with the URL, wherein one or more URL keywords are extracted from the website;

extracting one or more target keywords extracted from the advertisement information associated with the website, wherein the target keyword comprises the at least one first keyword registered by the advertiser;

determining, by the one or more processors, a value of a relevance between the URL keywords and the target keywords, wherein the value of the relevance is determined based on at least one of frequency of occurrence of a plurality of query sets by considering a first query and a second query as a query set, the second query being entered after the first query is entered, word statistics information obtained through words included in document sets existing on webs, documents, word classification with respect to the words or document classification with respect to the documents, and related search word sets being extracted from a related search word database provided by an Internet portal site; and

determining, by the processor, an index of each of the advertisement information, the index being an indication of whether an inspection is required for the advertisement information, according to the relevance value of between the URL keyword and the target keyword.

17. A system using a server comprising a processor for inspecting an advertisement, the system comprising:

a Universal Resource Locator (URL) keyword extraction component, of the processor, configured to crawl one or more websites associated with URLs to collect information of one or more URL keywords which are extracted from the crawled websites;

a target keyword extraction component, of the processor, configured to extract one or more target keywords comprising one or more advertising keywords extracted from advertisement information, the target keywords being registered by the advertiser, wherein the advertisement information comprises the URLs, one or more keywords for advertising and contents for advertising; and

a determination component, of the processor, configured to determine a relevance score between the URL keywords and the target keywords, the relevance score is determined by the processor based on at least one of frequency of occurrence of a plurality of query sets by considering a first query and a second query as a query set, the second query being entered after the first query is entered, word statistics information obtained through words included in document sets existing on webs, documents, word classification with respect to the words or document classification with respect to the documents, and related search word sets being extracted from a related search word database provided by an Internet portal site, and to determine an inspection index of the advertisement information, the inspection index being an indication of whether an inspection is required for the advertisement information according to the relevance score between the URL keywords and the target keywords.

18. The system of claim 17, wherein the URL keyword extraction component comprises:

a crawling component configured to crawl the one or more websites associated with the URLs, and

an extraction component configured to extract at least one URL keyword from contents of a web page linked by one of the URLs.

19. The system of claim 18, wherein the crawling component further comprises:

a representative web page collecting component configured to collect a representative web page which is directly linked by the URLs, and

a link collecting component configured to collect a web page which is linked to the representative web page.

20. The system of claim 17, wherein the contents for advertising comprise a title and a brief description of the one or more of the websites associated with the URL, the contents being displayed for the advertising.

21. The system of claim 17, wherein the determination component comprises:

an inspection index determination component configured to determine an inspection index of the advertisement information through keyword comparison between the extracted URL keyword and the target keyword; and

an attention-required inspection determination component configured to determine whether an inspection is required for the advertising by comparing the inspection index.

22. The system of claim 21, wherein the inspection index determination component further comprises:

a relevance score determination component configured to determine the relevance score of the target keyword with respect to the URL keyword, and

an index determination component configured to determine an inspection index of the plurality of advertisement information based on the determination.

23. The system of claim 22, wherein the index determination component further comprises:

a matching component configured to match the advertisement information to the relevance score of the target keyword extracted from the advertisement information; and

an average component configured to average the relevance score being matched to the advertisement information, and to determine whether the averaged relevance score to be an inspection index for the advertisement information.

24. The system of claim 21, wherein the inspection index is determined by comparing the relevance score with the advertisement information.

25. A system comprising a computer comprising a processor for inspecting an advertisement, the system comprising:

an issue keyword extraction component, of the processor, configured to extract at least one keyword associated with a buzzword related to social issues from at least one web page in response to receipt of advertisement information associated with advertising website of a user, the advertisement information comprising a Universal Resource Locator (URL), at least one keyword and advertising contents;

a URL keyword extraction component, of the processor, configured to collect one or more web pages by crawling the URL, wherein a URL keyword is extracted from contents of the collected web pages;

a target keyword extraction component, of the processor, configured to extract at least one target keyword from the advertisement information associated with the advertising website;

a determination component, of the processor, configured to determine a relevance score by using keyword comparison of the target keyword with respect to the URL keyword, the relevance score being determined based on at least one of frequency of occurrence of a plurality of query sets by considering a first query and a second query as a query set, the second query being entered after the first query is entered, word statistics information obtained through words included in document sets existing on webs, documents, word classification with respect to the words or document classification with respect to the documents, and related search word sets being extracted from a related search word database provided by an Internet portal site, wherein the determination component is further configured to determine an inspection index of the advertisement information, the inspection index being an indication of whether an inspection is required for the advertisement information according to the relationship between the buzzword and the target keyword.

26. The system of claim 25, wherein at least one web page comprises at least one online news article page and a real-time issue keyword page.

27. The system of claim 25, wherein the advertising contents comprises a title and a brief description of at least one website associated with the URL, the advertising contents being displayed for the advertising.

28. The system of claim 25, wherein the determination component further comprises:

a keyword determination component configured to search for a target keyword related to the keyword associated with the buzzword related to the social issues, and to determine the target keyword to be an attention-required inspection keyword; and

an attention-required inspection determination component configured to determine the advertisement information whether the attention-required inspection keyword is detected for further inspection.

29. The system of claim 28, wherein the keyword determination component further comprises:

an attention-required keyword determination component configured to determine a relevance score of the target keyword with respect to the keyword associated with the buzzword related to the social issues, and to determine the attention-required inspection keyword based on the relevance score.

30. The system of claim 28, further comprising:

a keyword exposing component configured to match the attention-required inspection keyword to the target keyword related to the attention-required inspection keyword, and to expose the matched result.