Profile prediction for shared computers

• US 9,536,000 B2
• Filed: 10/29/2010
• Issued: 01/03/2017
• Est. Priority Date: 10/29/2010
• Status: Expired due to Fees

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Excalibur IP, LLC (Acacia Research Corporation)
• Inventors: Ramaiyer, Viswanathan, Verma, Amit Kumar, Prakash, Hastagiri
• Primary Examiner(s): SOMERS, MARC S
• Application Number:
  US12/915,390
• Publication Number:
  US 20120109956A1
• Time in Patent Office: 2,258 Days
• Field of Search: 707/705, 707/736, 707/737, 705/14.4, 705/14.49, 705/14.52, 705/14.53, 705/14.66, 705/14.67, 705/14.73
• US Class Current: 1/1
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• 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 30/0277 Online advertisement

Abstract

A profile prediction system may identify one of multiple user profiles for a single computer. For example, a home computer may have multiple users that may not be targeted unless the user on the home computer can be identified. The system'"'"'s user identification may be based on a clustering model that considers various browsing characteristics to identify different clusters that each correspond to a particular user or user profile. The model may be generated and refined by tracking web browsing over multiple sessions. Future activity on the computer may be used to identify which user is the source of the activity and the user may receive targeted content including advertisements.

Claims

1. A non-transitory computer readable medium having stored therein data representing instructions executable by a programmed processor for identifying a user profile from a single source with multiple users and multiple user profiles, the storage medium storing instructions operative for:

identifying clusters of behavior from the multiple users of a single source using a session identification cookie to analyze a browsing history using tail sites and not using head sites to improve differentiation of clusters;

analyzing each of the clusters using a profile prediction model with a second cookie that stores the profile prediction model at the single source, the second cookie different from the session identification cookie;

developing a profile for each of the clusters from the session identification cookie based on the analysis of the clusters with the second cookie, wherein each of the multiple users are associated with one or more of the clusters;

monitoring behavior at the single source to identify one of the clusters based on the behavior, wherein the identified cluster is associated with one of the users of a developed profile for that identified cluster;

updating the profile prediction model based on the monitored behavior; and

targeting content based on the developed profile for that identified cluster.

2. The computer readable medium of claim 1 wherein the single source comprises a single computing device.

3. A system for identifying a user on a shared computing source comprising:

a web server coupled with a network and configured to receive requests from the source and return a page to the source in response to each of the requests;

an ad server coupled with the network and configured to provide advertisements with the pages returned in response to the requests;

a profile predictor comprising at least one processor, the profile predictor being coupled with the web server and the ad server and configured to analyze the requests with the at least one processor, the profile predictor comprising;

a cluster generator that analyzes sessions of the requests using a first cookie on the shared computing source and assigns each of the sessions to one of a plurality of clusters based on a browsing history using tail sites rather than head sites for more accuracy in clustering by the cluster generator;

a profile generator that determines characteristics for each of the clusters and generates a profile for each of the clusters that includes the determined characteristics for that cluster; and

a model generator that produces a model for associating a profile with requests received at the web server, wherein the model provides a probability that each of the users of the shared computing source belong to a particular cluster based on the determined characteristics.

4. The system of claim 3 wherein the model is stored with a second cookie and further wherein the first cookie and the second cookie are accessed from a web browser with the shared computing source.

5. The system of claim 3 wherein the source comprises a computer that is accessible by multiple users and the multiple users are each associated with one of the generated profiles.

6. The system of claim 5 wherein the model identifies one of the multiple users based on requests received at the web server.

7. The system of claim 3 wherein the ad server provides targeted advertisements in response to received requests that are targeted based on identifying a profile for those requests.

8. The system of claim 3 wherein response from the web server to the requests utilizes the model to target content for those requests based on profile associated with those requests.

9. The system of claim 3 wherein the generated profiles each comprise characteristics further including a first site visited, a second site visited, a most frequent site, a site with most time spent, site categories browsed, and/or time of day.

10. The system of claim 9 wherein the characteristics of the requests received at the web server are analyzed with the model for matching with one of the profiles.

11. The system of claim 3 wherein the generated profiles each comprise behavior data.

12. The system of claim 11 wherein the behavior data comprises browsing history, click history, or multimedia usage.

13. A method for identifying and predicting users of a computer, the method comprising:

generating a model that identifies the users, the generating comprising;

analyzing a plurality of sessions from the users on a single computer;

clustering the sessions based on one or more tail sites or torso sites visited during the particular session rather than head sites to improve differentiation of clusters;

generating a profile for each of the clusters, wherein each of the profiles is associated with one of the users; and

producing a model that associates common characteristics with the profile;

storing the model at least partially in a cookie on the computer; and

identifying, from the stored model, an active user from the users, the identifying comprising;

receiving requests from the computer;

analyzing, with the stored model, the common characteristics of the requests;

predicting the user submitting the requests from the computer based on the analysis; and

updating the stored model based on the requests and the analysis.

14. The method of claim 13 further comprising:

targeting the predicted user based on the profile associated with that user, wherein the targeting comprises targeted advertisements displayed in response to the requests.