Traffic prediction for web sites

• US 20070078958A1
• Filed: 09/19/2005
• Published: 04/05/2007
• Est. Priority Date: 09/19/2005
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Bennett, Victor
• Granted Patent: US 8,670,319 B2
• Time in Patent Office: Days
• US Class Current: 709/223
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: H04L 43/0888 Throughput

Abstract

A traffic prediction component may automatically generate predicted traffic profiles for web sites based on tags that characterize the sites. An initial set of tags can be selected for a web site based on a set of predefined rules. An initial traffic profile may be selected based on the initial set of tags. The predicted profile of user traffic is then generated based on the initial set of tags and on the initial traffic profile.

Claims

1. A computer-implemented method of predicting a profile of user traffic at a web site, the method comprising:

characterizing the web site based on at least one feature of the web site;

selecting an initial traffic profile based on the characterization of the web site; and

generating the predicted profile of user traffic based on the characterization of the web site and the initial traffic profile.

2. The method of claim 1, wherein the web site is characterized using a plurality of tags to describe the at least one feature of the web site.

3. The method of claim 2, wherein selecting the initial traffic profile includes selecting the initial traffic profile based on an observed traffic profile associated with another web site.

4. The method of claim 3, wherein selecting the initial traffic profile based on an observed traffic profile associated with another web site includes selecting the initial traffic profile associated with another web site that is associated with a second plurality of tags that are similar to the plurality of tags.

5. The method of claim 2, wherein generating the predicted profile of traffic includes recursively updating the plurality of tags and the predicted profile of traffic.

6. The method of claim 2, wherein the plurality of tags include tags that relate to an intended use of the site.

7. The method of claim 2, wherein the plurality of tags include tags that relate to an industry classification of the site.

8. The method of claim 2, wherein the plurality of tags include at least one of:

tags that indicate a primary language used by the site;

tags that relate to a geographical location of a host of the site;

or

tags that relate to a visual layout of the site.

9. The method of claim 1, wherein the traffic profile includes values that relate to how long a typical user will spend at the site.

10. The method of claim 1, wherein the traffic profile includes values relating to how many links a typical user will select at the site.

11. The method of claim 1, wherein the traffic profile includes values relating to a screen size of a typical user or a type of browser of the typical user.

12. The method of claim 2, further comprising:

heuristically determining initial values for the plurality of tags.

13. A computer-implemented method of modeling a web site comprising:

assigning an initial set of tags to the model based on features of the web site, each of the tags describing at least one feature of the web site;

determining an initial traffic profile for the web site based on the assigned initial set of tags; and

recursively updating the set of tags and the traffic profile to obtain a final predicted traffic profile for the web site.

14. The method of claim 13, wherein determining the initial traffic profile for the web site includes determining the initial traffic profile based on an observed traffic profile from another web site.

15. The method of claim 13, wherein determining the initial traffic profile includes selecting the initial traffic profile from another web site that is associated with a second set of tags similar to the initial set of tags.

16. The method of claim 13, where the initial set of tags includes tags that relate to an intended use of the site.

17. The method of claim 13, wherein the initial set of tags includes tags that relate to an industry classification of the site.

18. The method of claim 13, wherein the initial set of tags includes at least one of:

tags that indicate a primary language used by the site;

tags that relate to a geographical location of a host of the site;

or

tags that relate to a visual layout of the site.

19. The method of claim 13, wherein the initial traffic profile includes values that relate to how long a typical user will spend at the site.

20. The method of claim 13, wherein the initial traffic profile includes values relating to how many links a typical user will select at the site.

21. The method of claim 13, wherein the initial traffic profile includes values relating to a screen size of a typical user or a type of browser of the typical user.

22. A computer-readable medium containing instructions for execution by processing logic, the computer-readable medium including:

instructions for characterizing a web site based on at least one feature of the web site;

instructions for selecting an initial traffic profile based on the characterization of the web site; and

instructions for generating a profile predicting user traffic at the web site based on the characterization of the web site and the initial traffic profile.

23. The computer-readable medium of claim 22, wherein the web site is characterized using a plurality of tags to describe the at least one feature of the web site, and the computer-readable medium stores:

tags that relate to an intended use of the site;

or

tags that relate to an industry classification of the site.

24. A device comprising:

means for assigning an initial set of tags to a model of the web site based on features of the web site, each of the tags describing at least one feature of the web site;

means for determining an initial traffic profile for the web site based on the assigned initial set of tags; and

means for recursively updating the set of tags and the traffic profile to obtain a final predicted traffic profile for the web site.

25. A computer-implemented method of predicting a profile of user traffic at a web site, the method comprising:

determining an initial set of tags that characterize at least one feature of the web site based on a set of predefined rules, the initial set of tags including a tag that relates to an intended use of the site or a tag that relates to an industry classification of the site;

selecting an initial traffic profile based on a comparison of the initial set of tags to tags determined for other web sites to locate those of the other web sites that are similar to the web site;

recursively updating the traffic profile and the set of tags to generate a model of the web site;

using the model to predict traffic at the web site;

comparing the predicted traffic to observed traffic; and

outputting a signal when the observed traffic does not match the predicted traffic.