Method for click-stream analysis using web directory reverse categorization
Information on a click stream associated with a user and meta tags commonly used by search engines can be used to profile a user. The click stream may comprise network addresses and timestamps and may be the only source of user information used for the profile. The meta tags may contain metadata that correspond to the network addresses in the click stream, including network address categorization for these network addresses. The profile obtained for the user may be an existing profile that represents a person or a theoretical individual having attributes similar to or most closely match the user. Based at least in part on the profile, information regarding an item may be provided to the user or the item may be offered to the user. Information may be filtered before being displayed to the user.
1. A system, comprising:
a server computer having a processor,
a non-transitory computer readable medium; and
stored instructions translatable by the processor to perform:
receiving a click stream associated with a user, the click stream collected while the user on a client computer browsed a network, wherein the click stream comprises network addresses requested by the user;
analyzing the click stream to obtain network addresses requested by the user;
storing a user identifier for the user, the network addresses requested by the user and temporal information corresponding to the network addresses requested by the user;
retrieving search engine categorization information for the network addresses requested by the user from a search engine system that categorizes network addresses across a plurality of network domains, the search engine categorization information comprising categories corresponding to the network addresses requested by the user;
storing user profile data for the user, wherein storing the user profile data for the user comprises storing, in association with the user identifier and temporal information, the categories corresponding to the network addresses requested by the user;
generating a user profile for the user, generating the user profile for the user comprising:
identifying, from a set of existing user profiles, an existing profile that most closely matches the user profile data for the user based at least in part on a comparison of the categories corresponding to the network addresses requested by the user to the set of existing user profiles;
associating the user with the existing profile that most closely matches the user profile data for the user;
selecting, based on the user profile for the user, web page content for inclusion in a web page to be provided to the client computer in response to a request associated with the user, wherein selecting the web page content comprises selecting a first set of information based on the user profile and applying a filter to the first set of information to remove information from the first set of information to determine the web page content; and
providing the web page content to a network site for inclusion by the network site in the web page.
2. The system of claim 1 , wherein the set of existing user profiles comprises user profiles generated for other users.
3. The system of claim 1 , wherein the search engine categorization information comprises meta tags.
4. The system of claim 1 , wherein the click stream associated with the user is a HyperText Transfer Protocol stream.
5. The system of claim 1 , wherein the filter comprises a filter configured to remove content that has previously been seen by the user.
6. The system of claim 1 , wherein the filter comprises a filter configured to remove offensive content.
7. The system of claim 1 , wherein the web page content comprises content configured for display at a periphery of the web page.
8. The system of claim 1 , wherein the click stream associated with the user is the sole source of user Information for that user used to generate the user profile.
9. The system of claim 1 , wherein the set of existing user profiles comprises a profile for a theoretical individual.
10. A computer program product comprising a non-transitory computer readable medium storing instructions translatable by a processor to perform:
receiving a click stream associated with a user, the click stream collected while the user browsed a network on a client computer, wherein the click stream comprises network addresses requested by the user;
analyzing the click stream to obtain network addresses requested by the user;
storing a user identifier for the user, the network addresses requested by the user and temporal information corresponding to the network addresses requested by the user in first data structure;
retrieving search engine categorization information for the network addresses requested by the user from a search engine system that categorizes network addresses across a plurality of network domains, the search engine categorization information comprising categories corresponding to the network addresses requested by the user;
storing user profile data for the user, wherein storing the user profile data for the user comprises storing, in association with the user identifier and temporal information, the categories corresponding to the network addresses requested by the user;
generating a user profile for the user, generating the user profile for the user comprising:
identifying, from a set of existing user profiles, an existing profile that most closely matches the user profile data for the user based at least in part on a comparison of the categories corresponding to the network addresses requested by the user to the set of existing user profiles; and
associating the user with the existing profile that most closely matches the user profile data for the user;
selecting, based on the user profile for the user, web page content for inclusion in a web page to be provided to the client computer in response to a request associated with the user, wherein selecting the web page content comprises selecting a first set of information based on the user profile and applying a filter to the first set of information to remove information from the first set of information to determine the web page content; and
providing the web page content to a network site for inclusion by the network site in the web page.
11. The computer program product of claim 10 , wherein the set of existing user profiles comprises user profiles generated for other users.
12. The computer program product of claim 10 , wherein the search engine categorization information comprises meta tags.
13. The computer program product of claim 10 , wherein the click stream associated with the user is a HyperText Transfer Protocol stream.
14. The computer program product of claim 10 , wherein the filter comprises a filter configured to remove content that has previously been seen by the user.
15. The computer program product of claim 10 , wherein the filter comprises a filter configured to remove offensive content.
16. The computer program product of claim 10 , wherein the web page content comprises content configured for display at a periphery of the web page.
17. The computer program product of claim 10 , wherein the click stream associated with the user is the sole source of user information for that user used to generate the user profile.
18. The computer program product of claim 10 , wherein the set of existing user profiles comprises a profile for a theoretical individual.