SYSTEM AND METHOD FOR PERSONALIZED SEARCH

• US 20090248682A1
• Filed: 04/01/2009
• Published: 10/01/2009
• Est. Priority Date: 04/01/2008
• Status: Active Grant

• Current Assignee: Certona Corporation (StartApp, Inc.)
• Original Assignee: Certona Corporation (StartApp, Inc.)
• Inventors: Hueter, Geoffrey J., Quandt, Steven C.
• Granted Patent: US 8,903,811 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 30/00 Commerce
• CPC Class Codes: G06Q 30/0185 Product, service or business identity fraud
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 30/0204 Market segmentation
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: H04L 51/212 using filtering or selective blocking

Abstract

A system and method is disclosed for profiling a subject'"'"'s search engine keywords and results based on relevancy feedback. Because the system is based on the search behavior of the user, the profiling is language independent and balances the specificity of search terms against the profiled interests of the user. The system can also synthesize new keyword combinations to assist the user in refining the search or acquiring related content. The system has application in text mining, personalization, behavioral search, search engine optimization, and content acquisition, to name but a few applications.

Claims

1. A system for personalized search, comprising:

(a) a service system for searching, collecting relevancy feedback, and acquiring content;

(b) subjects and objects represented in vector form;

(c) optimal subject and object vectors derived solely from said subject'"'"'s relevancy ratings of objects; and

(d) search results to, and collecting relevancy ratings from, an external application;

whereby said system does not need to know anything about object content, does not need to know anything about subject demographics, employs statistical/neural network modeling by means of input modeling rather than transfer function, uses a fixed size profile for subjects and objects for scalable processing,

all accomplished in a mentor-less and self-optimizing fashion, scalable to large numbers of users and objects.

2. The system for personalized search, according to claim 1, wherein said service system for searching, collecting relevancy feedback, and acquiring content includes generating relevancy ratings that are implicit or explicit.

3. The system for personalized search, according to claim 1, wherein said subject and object vectors include subject vector of search users and object vectors of search keywords and search results.

4. The system for personalized search, according to claim 3, wherein said search keyword object vectors are matched to said search result objects to generate behavioral relevancy scores.

5. The system for personalized search, according to claim 3, wherein said keywords and content include keywords and content of different languages.

6. The system for personalized search, according to claim 1, wherein said service system for searching, collecting relevancy feedback, and acquiring content includes combining user behavioral search relevancy scores with textual search relevancy scores.

7. The system for personalized search, according to claim 1, wherein said optimal subject and object vectors derived solely from said subject'"'"'s relevancy ratings of objects includes weighting the relevancy ratings of expert users higher the relevancy ratings of non-experts.

8. The system for personalized search, according to claim 2, wherein the weighting of said implicit ratings are increased for repeated occurrences of an interaction, either viewing or not viewing a search result.

9. The system for personalized search, according to claim 1, wherein said service system for searching, collecting relevancy feedback, and acquiring content includes acquiring content through synthesis of multiple keywords.

10. The system for personalized search, according to claim 1, wherein said service system for searching, collecting relevancy feedback, and acquiring content includes clustering search result object vectors to identify content regions of interest to the search user.

11. A method for personalized search, comprising the steps of:

(a) providing a service system for searching, collecting relevancy feedback, and acquiring content;

(b) providing subjects and objects represented in vector form;

(c) calculating optimal subject and object vectors derived solely from said subject'"'"'s relevancy ratings of objects; and

(d) providing search results to, and collecting relevancy ratings from, an external application;

whereby said system does not need to know anything about object content, does not need to know anything about subject demographics, employs statistical/neural network modeling by means of input modeling rather than transfer function, uses a fixed size profile for subjects and objects for scalable processing,

all accomplished in a mentor-less and self-optimizing fashion, scalable to large numbers of users, keywords, and objects.

12. The method for personalized search, according to claim 11, wherein said step of providing a service system for searching, collecting relevancy feedback, and acquiring content includes the step of providing a service system for searching, collecting relevancy feedback, and acquiring content wherein said service system for searching, collecting relevancy feedback, and acquiring content includes generating relevancy ratings that are implicit or explicit.

13. The method for personalized search, according to claim 11, wherein said step of providing subjects and objects represented in vector form includes the step of providing subjects and objects represented in vector form wherein said subject and object vectors include subject vector of search users and object vectors of search keywords and search results, and further wherein said search keyword object vectors are matched to said search result objects to generate behavioral relevancy scores.

14. The method for personalized search, according to claim 13, wherein said step of matching keyword object vectors to said search result objects to generate behavioral relevancy scores includes the step of matching keyword object vectors wherein said keywords and content include keywords and content of different languages.

15. The method for personalized search, according to claim 11, wherein said step of providing a service system for searching, collecting relevancy feedback, and acquiring content includes the step of providing a service system for searching, collecting relevancy feedback, and acquiring content wherein said service system for searching, collecting relevancy feedback, and acquiring content includes combining user behavioral search relevancy scores with textual search relevancy scores.

16. The method for personalized search, according to claim 11, wherein said step of calculating optimal subject and object vectors derived solely from said subject'"'"'s relevancy ratings of objects includes the step of calculating optimal subject and object vectors derived solely from said subject'"'"'s relevancy ratings of objects wherein said optimal subject and object vectors derived solely from said subject'"'"'s relevancy ratings of objects includes weighting the relevancy ratings of expert users higher than the relevancy ratings of non-experts, and further wherein the weighting of said implicit ratings are increased for repeated occurrences of an interaction, either viewing or not viewing a search result.

17. The method for personalized search, according to claim 11, wherein said step of providing a service system for searching, collecting relevancy feedback, and acquiring content includes the step of providing a service system for searching, collecting relevancy feedback, and acquiring content wherein said service system for searching, collecting relevancy feedback, and acquiring content includes acquiring content through synthesis of multiple keywords.

18. The method for personalized search, according to claim 11, wherein said step of providing a service system for searching, collecting relevancy feedback, and acquiring content includes the step of providing a service system for searching, collecting relevancy feedback, and acquiring content wherein said service system for searching, collecting relevancy feedback, and acquiring content includes clustering search result object vectors to identify content regions of interest to the search user.

19. A method for using a system for personalized search, comprising the steps of:

(a) submitting keywords;

(b) presenting search results;

(c) selecting a search result;

(d) rating the relevancy of the search result;

(e) updating user, keyword, and search result profiles;

(f) re-matching keyword and content profiles and re-displaying search results; and

(e) clustering and synthesizing keywords;

whereby said system generates targeted search results to each user and self-optimizes keyword profiles to optimize the relevancy of the search results for each user.

20. The method for using a system for personalized search, according to claim 19, wherein said step of submitting keywords includes the step of searching for products or content on a website.