CLICKSTREAMS AND WEBSITE CLASSIFICATION

• US 20110137904A1
• Filed: 12/03/2009
• Published: 06/09/2011
• Est. Priority Date: 12/03/2009
• Status: Active Grant

• Current Assignee: Micro Focus LLC (Open Text Corporation)
• Original Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Inventors: Scholz, Martin B., Rajaram, Shyam Sundar, Lukose, Rajan
• Granted Patent: US 9,256,692 B2
• Time in Patent Office: Days
• US Class Current: 707/740
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 16/355 Class or cluster creation or modification
• CPC Class Codes: G06F 16/955 using information identifiers, e.g. uniform resource locators [URL]
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

One embodiment is a method that receives a seed Uniform Resource Locator (URL) that represents a category for website classification. Clickstream data generated from the seed URL and additional URLs are analyzed to determine whether the additional URLs belong to the category. The method selects one or more of the additional URLs to represent the category.

Claims

1. ) A method executed by a computer, comprising:

receiving a seed Uniform Resource Locator (URL) that represents a category for website classification;

analyzing clickstream data generated from the seed URL and additional URLs to determine whether the additional URLs belong to the category; and

selecting one or more of the additional URLs to represent the category.

2. ) The method of claim 1 further comprising, building a website classification model based on the seed URL and additional URLs, the website classification model being executable to analyze the clickstream data and determine whether URLs belong to the category.

3. ) The method of claim 1 further comprising, analyzing a number of clicks that a user performs at each of the additional URLs to determine whether the additional URLs are related to the seed URL and represent the category.

4. ) The method of claim 1 further comprising, analyzing an amount of time that users spend at each of the additional URLs to determine whether the additional URLs are related to the seed URL and represent the category.

5. ) The method of claim 1, wherein the clickstream data includes at least one of a record of each URL visited, a timestamp when the URL is visited, or a unique identification for each user.

6. ) The method of claim 1 further comprising:

iteratively adding more URLs to the category;

iteratively discovering users who belong to the category.

7. ) The method of claim 1 further comprising, tracking clickstreams of a user to generate a candidate list of URLs to represent the category.

8. ) A method executed by a computer, comprising:

building a website classification model that uses a seed Uniform Resource Locator (URL) to represent a category and analyzes clickstreams navigating to the seed URL and additional URLs to determine whether the additional URLs belong to the category.

9. ) The method of claim 8 further comprising, building user profile models from the clickstreams.

10. ) The method of claim 8, wherein the website classification model tracks a plurality of levels of a URL path for each of the additional URLs.

11. ) The method of claim 8, wherein the website classification model computes a frequency of clicks of the additional URLs in the clickstreams to determine if the additional URLs belong to the category.

12. ) The method of claim 8 wherein the website classification model selects one of the additional URLs as a second seed URL and analyzes the clickstream to determine which of the additional URLs relate to both the seed and second URLs and represent the category.

13. ) The method of claim 8, wherein the website classification model determines whether the additional URLs belong to the category without reviewing text or images presented at web pages of the additional URLs.

14. ) The method of claim 8, wherein the clickstreams are generated as the users click to the seed URL and the additional URLs.

15. ) A tangible computer-readable medium having instructions for causing a computer to execute a method, comprising:

obtaining a seed Uniform Resource Locator (URL) that represents a category for website classification;

analyzing clickstreams that navigate to the seed URL and additional URLs to determine which of the additional URLs belong to the category; and

generate, from the additional URLs, a list of URLs that represent the category.

16. ) The tangible computer-readable medium of claim 15 further comprising, building, from the list of URLs, user profiles.

17. ) The tangible computer-readable medium of claim 15 further comprising, updating the list of URLs to reflect new interests of a user based on changes to the clickstreams of the user.

18. ) The tangible computer-readable medium of claim 15 further comprising, applying the list of URLs to provide target advertising to a user.

19. ) The tangible computer-readable medium of claim 15 further comprising, determining an average number of clicks a user perform at the additional. URLs to determine which of the additional URLs belong to the category.

20. ) The tangible computer-readable medium of claim 15 further comprising, matching the seed URL with the clickstreams to determine which of the additional URLs belong to the category.