Content based web advertising

• US 6,804,659 B1
• Filed: 01/14/2000
• Issued: 10/12/2004
• Est. Priority Date: 01/14/2000
• Status: Expired due to Term

• Current Assignee: Ricoh Company Limited
• Original Assignee: Ricoh Company Limited
• Inventors: Graham, Jamey, Stork, David G.
• Primary Examiner(s): Stamber, Eric W.
• Assistant Examiner(s): CHAMPAGNE, DONALD
• Application Number:
  US09/483,092
• Time in Patent Office: 1,733 Days
• Field of Search: 705/14
• US Class Current: 705/14.49
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0277 Online advertisement

Abstract

According to the present invention, an internet target marketing system, method and computer program for distributing online advertising to viewers based upon the viewers'"'"' interests is provided. Specific embodiments according to the present invention can use an n-way matching of user'"'"'s concepts of interest, advertiser'"'"'s concepts and a currently viewed document to target advertising to the view of the current document. Some embodiments can generate a contextually sensitive advertisement for each page viewed in a browser, thereby associating an advertisement with every page in a document. Specific embodiments can associate advertising with documents that are substantially free of embedded advertisements, for example. Alternative embodiments can include embedded advertising, however.

Claims

1. A method for targeting advertising to a user based upon content of a document displayed to said user, said method comprising:

comparing said content of said document to user selectable concepts of interest to identify the user selectable concepts of interest that are relevant to said document;

comparing said content of said dicynetb ti advertiser selectable concepts of interest to identify the advertiser selectable concepts of interest that are relevant to said document;

comparing said relevant user selectable concepts of interest to said relevant advertiser selectable concepts of interest to determine an overall relevance; and

selecting an advertising based upon said overall relevance.

2. The method of claim 1 further comprising displaying said selected advertising in a marketing information area of a web browser.

3. The method of claim 1 wherein said comparing said relevant user selectable concepts of interest further comprises:

measuring a similarity between a first set of terms and a second set of terms;

wherein said first set of terms comprises said user concepts and said second set of terms comprises said advertiser concepts.

4. The method of claim 1 wherein said comparing said relevant user seletable concepts of interest further comprises;

measuring a term frequency between a first vector C and a second vector A;

wherein said first vector comprises said user concepts, c_i, and said second vector comprises said advertiser concepts, a_j;

said first vector having m user concepts and said second vector having n advertiser concepts; and

comparing said first vector and said second vector to obtain a third vector V_ij;

wherein said third vector comprises an indication of a match of concepts common to said first vector and said second vector.

5. The method of claim 4 further comprising:

determining a number of indications of matches, W_ij in said third vector, V_ij;

determine a length, X_i, of said third vector, V_ij;

determining a value, c_i; and

determining a similarity value, S_ij, according to the relationship;

$S_{\mathrm{ij}}^{\mathrm{\prime <br><br>}}=\left(\frac{W_{\mathrm{ij}}}{X_i}\right)\times <br><br>c_i.$

6. The method of claim 5 further comprising:

determining said relevancy, R_j, according to the relationship;

$R_j=\left(\underset{i}{\overset{m}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br>S_{\mathrm{ij}}\right)\times <br><br>a_j.$

7. A system for providing targeted advertising to a user based upon a content of a document displayed to said user, said system comprising:

a profile content recognizer that compares said content of said document to at least one of a plurality of user selectable concepts to identify the user selectable concepts that are relevant to said content of said document;

an advertising content recognizer that compares said content of said document to said at least one of a plurality of advertiser selectable concepts to identify the advertiser selectable concepts that are relevant to said document; and

a comparator that compares said relevant user selectable concepts with said relevant advertiser selectable concepts to identify one or more most relevant advertiser concepts, and selects from a plurality of stored advertisements ones that are relevant to the information contained in said document based upon said one or more most relevant advertiser concepts.

8. The system of claim 7 wherein said advertising content recognizer selects a best advertisement from said stored advertisements.

9. A computer program product for targeting advertising to a user based upon a content of a document displayed to said user, said computer program product comprising:

code for comparing said content of said document to at least one of a plurality of user selectable concepts of interest to identify the user selectable concepts of interest that are relevant to said content of said document;

code for comparing said content of said document to at least one of a plurality of advertiser selectable concepts of interest to identify the advertiser selectable concepts of interest that are relevant to said content of said document;

code for comparing said relevant user selectable concepts of interest to said relevant advertiser selectable concepts of interest to determine an overall relevance;

code for selecting an advertising based upon said overall relevance; and

a computer readable storage medium for holding the codes.

10. A method for automatically associating advertising objects with web objects, said method comprising:

comparing a web object to first concepts of interest to identify one or more of the first concepts of interest that are relevant to said web object;

comparing said web object to second concepts of interest to identify one or more of the second concepts of interest that are relevant to said web object;

determining an overall relevance between said relevant first concepts of interest and said relevant second concepts of interest; and

associating said web object with an advertising object based upon said overall relevance.

11. The method of claim 10 wherein said determining further comprises:

measuring a similarity between a first set of terms and a second set of terms;

wherein said first set of terms comprises said first concepts of interest and said second set of terms comprises said second concepts of interest.

12. The method of claim 10 wherein said determining an overall relevance between said relevant first concepts of interest and said relevant second concepts of interest further comprises:

measuring a term frequency between a first vector C and a second vector A;

wherein said first vector comprises said first concepts of interest, c_i, and said second vector comprises said second concepts of interest, a_j;

said first vector having m concepts and said second vector having n concepts; and

comparing said first vector and said second vector to obtain a third vector V_ij, wherein said third vector comprises an indication of a match of concepts common to said first vector and said second vector.

13. The method of claim 12 further comprising:

determining a number of indications of matches, W_ij in said third vector, V_ij;

determining a length, X_i, of said third vector, V_ij;

determining a value, c_i; and

determining a similarity value, S_ij, according to the relationship;

$S_{\mathrm{ij}}^{\mathrm{\prime <br><br>}}=\left(\frac{W_{\mathrm{ij}}}{X_i}\right)\times <br><br>c_i.$

14. The method of claim 13 further comprising:

determining said overall relevance, R_j, according to the relationship;

$R_j=\left(\underset{i}{\overset{m}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br>S_{\mathrm{ij}}\right)\times <br><br>a_j.$

15. The method of claim 14 further comprising displaying said advertising in a marketing information area of a web browser.

16. A computer program product for automatically associating advertising objects with web objects, said product comprising:

code for analyzing a web object to identify information corresponding to first concepts of interest that are relevant to said web object;

code for analyzing said web object to identify information corresponding to second concepts of interest that are relevant to said web object;

code for determining a relevance between said first concepts of interest and said second concepts of interest;

code for associating said web object with said at least one advertising object based upon said relevance; and

a computer readable storage medium for holding the codes.