Personalization of placed content ordering in search results

• US 7,693,827 B2
• Filed: 07/13/2004
• Issued: 04/06/2010
• Est. Priority Date: 09/30/2003
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Fikes, Andrew B., Zamir, Oren Eli, Lawrence, Stephen R., Korn, Jeffrey L.
• Primary Examiner(s): Breene; John E
• Assistant Examiner(s): LE, THU NGUYET T
• Application Number:
  US10/890,854
• Publication Number:
  US 20050240580A1
• Time in Patent Office: 2,093 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: H04L 67/025 for remote control or remote monitoring of applications
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching

Abstract

A system and method for using a user profile to order placed content in search results returned by a search engine. The user profile is based on search queries submitted by a user, the user'"'"'s specific interaction with the documents identified by the search engine and personal information provided by the user. Placed content is ranked by a score based at least in part on a similarity of a particular placed content to the user'"'"'s profile. User profiles can be created and/or stored on the client side or server side of a client-server network environment.

Claims

1. A computer-implemented method of personalizing placed content associated with a search query, comprising:

at a server system having one or more processors and memory storing programs executed by the one or more processors;

receiving a search query from a user;

accessing a user profile associated with the user, wherein the user profile is based, at least in part, on query terms in a plurality of previously submitted search queries;

identifying a set of placed content that matches the search query;

assigning a popularity score to each of the set of placed content in accordance with the user profile, a respective bid value for the placed content, and a respective click through rate for the placed content based on multiple user activities, wherein the assigning the popularity score includes;

determining a similarity score between the user profile and a placed content profile associated with the placed content, wherein the similarity score is indicative of a level of similarity between the user profile and the associated placed content profile, and

combining the similarity score with the respective click through rate and the respective bid value to determine the popularity score assigned to the placed content; and

ranking the set of placed content according to their respective popularity scores; and

preparing for display to the user at least a subset of the set of placed content in an order determined by their respective popularity scores.

2. The method of claim 1, wherein the user profile is based, at least in part, on information about the user, including information derived from a set of documents, the set of documents comprising a plurality of documents selected from the set consisting of documents identified by search results from a search engine, documents linked to the documents identified by search results from the search engine, documents linked to the documents accessed by the user, and documents browsed by the user.

3. The method of claim 1, wherein the determining of the similarity score includes

determining a mathematical distance between a user profile vector of the user profile, the user profile vector including first pairs of categories and respective weights, and a placed content profile vector of the placed content, the placed content profile vector including second pairs of categories and respective weights.

4. The method of claim 1, further including associating the similarity score with a scaling factor.

5. The method of claim 1, further including normalizing the similarity score to a particular range to create a scaling factor.

6. The method of claim 4, wherein the assigning the popularity score to each of the set of placed content includes multiplying the scaling factor, the respective click through rate and the respective bid value.

7. The method of claim 6, wherein the scaling factor associated with a maximum similarity score is less than the scaling factor associated with a mid-point similarity score.

8. The method of claim 4, wherein the scaling factor is determined in accordance with statistical information relating similarity scores to click through rates.

9. The method of claim 1, further including providing the placed content as an advertisement.

10. A computer system for personalizing placed content associated with a search query, comprising:

a user profile, based, at least in part, on query terms in a plurality of previously submitted search queries; and

a placed content server, including a plurality of placed content, for identifying a subset of the plurality of placed content that matches a search query and that assigns a popularity score to each of the plurality of placed content in the subset in accordance with the user profile, a respective bid value for the placed content, and a respective click through rate for the placed content based on multiple user activities, and that ranks the subset based on the respective popularity scores of the subset of placed content, and that prepares for display of the subset of the plurality of placed content in an order determined by their respective popularity scores,

wherein the popularity score of each piece of placed content is based on a similarity score between the user profile and a placed content profile associated with the placed content, wherein the similarity score is indicative of a level of similarity between the user profile and the associated placed content profile, and

wherein the similarity score is combined with the respective click through rate and the respective bid value to determine the popularity score assigned to the placed content.

11. The system of claim 10, wherein the user profile is based, at least in part, on information about the user, including information derived from a set of documents, the set of documents comprising a plurality of documents selected from the set consisting of documents identified by search results from a search engine, documents linked to the documents identified by search results from the search engine, documents linked to the documents accessed by the user, and documents browsed by the user.

12. The system of claim 10, wherein the similarity score is based on a mathematical distance between a user profile vector of the user profile, the user profile vector including first pairs of categories and respective weights, and a placed content profile vector of the placed content, the placed content profile vector including second pairs of categories and respective weights.

13. The system of claim 10, further including a scaling factor associated with the similarity score.

14. The system of claim 13, wherein the scaling factor is determined by normalizing the similarity score to a particular range.

15. The system of claim 13, wherein the popularity score of each piece of placed content in the set of placed content corresponds to the multiplicative product of the respective scaling factor, the respective click through rate and the respective bid value for the placed content.

16. The system of claim 15, wherein the scaling factor associated with a maximum similarity score is less than the scaling factor associated with a mid-point similarity score.

17. The system of claim 13, wherein the scaling factor is based on statistical information relating similarity scores to click through rates.

18. The system of claim 10, wherein the placed content is an advertisement.

19. A computer program product embodied on a computer readable medium, the computer program product comprising one or more programs that are stored on the computer readable medium and that are executable by a computer so as to perform a process, the one or more computer programs of the computer program product comprising:

instructions for receiving a search query from a user;

instructions for accessing a user profile associated with the user, wherein the user profile is based, at least in part, on query terms in a plurality of previously submitted search queries;

instructions for identifying a set of placed content that matches the search query;

instructions for assigning a popularity score to each of the set of placed content in accordance with the user profile, a respective bid value for the placed content, and a respective click through rate for the placed content based on multiple user activities, wherein the instructions for assigning the popularity score include;

instructions for determining a similarity score between the user profile and a placed content profile associated with the placed content, wherein the similarity score is indicative of a level of similarity between the user profile and the associated placed content profile, and

instructions for combining the similarity score with the respective click through rate and the respective bid value to determine the popularity score assigned to the placed content;

instructions for ranking the set of placed content according to their respective popularity scores; and

instructions for preparing for display to the user at least a subset of the set of placed content in an order determined by their respective popularity scores.

20. The computer program product of claim 19, wherein the user profile is based, at least in part, on information about the user, including information derived from a set of documents, the set of documents comprising a plurality of documents selected from the set consisting of documents identified by search results from a search engine, documents linked to the documents identified by search results from the search engine, documents linked to the documents accessed by the user, and documents browsed by the user.

21. The computer program product of claim 19, wherein the instructions for determining the similarity score include determining a mathematical distance between a user profile vector of the user profile, the user profile vector including first pairs of categories and respective weights, and a placed content profile vector of the placed content, the placed content profile vector including second pairs of categories and respective weights.

22. The computer program product of claim 19, further including instructions for associating the similarity score with a scaling factor.

23. The computer program product of claim 21, further including instructions for normalizing the similarity score to a particular range to create a scaling factor.

24. The computer program product of claim 22, wherein the instructions for assigning the popularity score to each of the set of placed content includes instructions for multiplying the scaling factor, the respective click through rate and the respective bid value.

25. The computer program product of claim 24, wherein the scaling factor associated with a maximum similarity score is less than the scaling factor associated with a mid-point similarity score.

26. The computer program product of claim 22, wherein the scaling factor is determined in accordance with statistical information relating similarity scores to click through rates.

27. The computer program product of claim 19, wherein the placed content is an advertisement.

28. A computer-implemented method of personalizing placed content associated with a search query, comprising:

receiving a search query from a user;

accessing a user profile associated with the user, wherein the user profile is based, at least in part, on query terms in a plurality of previously submitted search queries;

identifying a set of placed content based on contents of one or more documents being presented as search results to the search query;

assigning a popularity score to each of the set of placed content in accordance with the user profile, a respective bid value for the placed content, and a respective click through rate for the placed content based on multiple user activities, wherein the assigning the popularity score includes;

determining a similarity score between the user profile and a placed content profile associated with the placed content, wherein the similarity score is indicative of a level of similarity between the user profile and the associated placed content profile, and

combining the similarity score with the respective click through rate and the respective bid value to determine the popularity score assigned to the placed content; and

ranking the set of placed content according to their respective popularity scores; and

preparing for display to the user at least a subset of the set of placed content in an order determined by their respective popularity scores.

29. A computer-implemented method of personalizing placed content associated with a search query, comprising:

receiving a request from a user for a document;

accessing a user profile associated with the user, wherein the user profile is based, at least in part, on query terms in a plurality of previously submitted search queries;

identifying a set of placed content based on contents of the document being requested by the user;

assigning a popularity score to each of the set of placed content in accordance with the user profile, a respective bid value for the placed content, and a respective click through rate for the placed content based on multiple user activities, wherein the assigning the popularity score includes;

determining a similarity score between the user profile and a placed content profile associated with the placed content, wherein the similarity score is indicative of a level of similarity between the user profile and the associated placed content profile, and

combining the similarity score with the respective click through rate and the respective bid value to determine the popularity score assigned to the placed content; and

ranking the set of placed content according to their respective popularity scores; and

preparing for display to the user at least a subset of the set of placed content in an order determined by their respective popularity scores.