ANONYMOUS PERSONALIZED RECOMMENDATION METHOD

• US 20130226946A1
• Filed: 02/27/2012
• Published: 08/29/2013
• Est. Priority Date: 02/27/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Mourad, Shibl, Phillips, Caitlin Kelly, Courteau, Marc-Antoine, Beaudoin, Philippe
• Granted Patent: US 8,521,735 B1
• Time in Patent Office: Days
• US Class Current: 707/758
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 21/6254 by anonymising data, e.g. decorrelating personal data from the owner's identification

Abstract

A computer-implemented method for an anonymous personalized recommendation is provided. The method includes receiving select server fingerprints selected from server fingerprints based on predetermined metrics. The server fingerprints correspond to a plurality of public entities and each server fingerprint includes encoded information about a corresponding public entity. The method also includes generating a user fingerprint based on user information associated with a user, the user fingerprint comprising encoded user information. The method further includes comparing the user fingerprint with the select server fingerprints to select a server fingerprint for recommendation, and generating a recommendation of a public entity corresponding to the server fingerprint for recommendation. Systems and machine-readable media are also provided.

Claims

1. A computer-implemented method for anonymously recommending public entities, the method comprising:

receiving, at a client from a server, select server fingerprints selected from server fingerprints based on predetermined metrics, the server fingerprints corresponding to a plurality of public entities, each server fingerprint comprising encoded information about a corresponding public entity, wherein the encoded information is encoded to compress a size of the each server finger print;

generating, at the client, a user fingerprint based on user information associated with a user, the user fingerprint comprising encoded user information;

comparing, at the client, the user fingerprint with the select server fingerprints to select a server fingerprint for recommendation; and

generating, at the client, a recommendation of a public entity corresponding to the server fingerprint for recommendation.

2. The method of claim 1, further comprising receiving a search result based on an information search request made by the user and modifying the search result based on the generated recommendation.

3. The method of claim 1, further comprising storing the received select server fingerprints in a data store.

4. The method of claim 3, further comprising:

updating the user fingerprint based on user feedback;

comparing the updated user fingerprint with the stored select server fingerprints to select an updated server fingerprint for recommendation; and

generating an updated recommendation of a public entity corresponding to the updated server fingerprint for recommendation.

5. The method of claim 1, wherein the plurality of public entities comprise at least one of a web site, an article, a blog, and a user on a social networking site.

6. The method of claim 1, wherein the encoded information about the corresponding public entity comprises relevancy values corresponding to a plurality of keywords, each of the relevancy values representing relevancy of the corresponding public entity to each keyword.

7. The method of claim 1, wherein the user information comprises at least one of a search history of the user, web page access history of the user, and web page bookmarks of the user.

8. The method of claim 1, wherein the encoded user information comprises relevancy values corresponding to a plurality of keywords, each of the relevancy values representing relevancy of the user information to each keyword.

9. The method of claim 1, wherein the select server fingerprints are selected based on popularity of the corresponding public entity.

10. The method of claim 1, wherein the select server fingerprints are selected based on at least one of a category of public entities requested by the user, geographic location associated with the user, and language requested by the user.

11. The method of claim 1, further comprising communicating a request for the select server fingerprints to a server by conforming to a network protocol;

wherein the select server fingerprints are received in response to the request for the select server fingerprints.

12. The method of claim 11, wherein in the step of selecting the server fingerprints to communicate to the client, the server fingerprints are selected based on information generated as part of the network protocol.

13. A system for anonymously recommending public entities, the system comprising:

a memory storing executable instructions; and

a processor coupled to the memory configured to execute the stored executable instructions to;

receive select server fingerprints, wherein the select server fingerprints are selected from server fingerprints based on predetermined metrics, and wherein the server fingerprints correspond to a plurality of public entities, each server fingerprint comprising encoded information about a corresponding public entity, the encoded information being encoded to compress a size of the each server finger print;

generate a user fingerprint based on user information associated with a user, the user fingerprint comprising encoded user information;

compare the user fingerprint with the select server fingerprints to select a server fingerprint for recommendation;

generate a recommendation of a public entity corresponding to the server fingerprint for recommendation;

receive a search result based on an information search request made by the user; and

modify the search result based on the generated recommendation.

14. The system of claim 13, further comprising a data store, wherein the processor is further configured to:

store the select server fingerprints in the data store;

update the user fingerprint based on user feedback;

compare the updated user fingerprint with the stored select server fingerprints to select an updated server fingerprint for recommendation; and

generate an updated recommendation of a public entity corresponding to the updated server fingerprint for recommendation.

15. The system of claim 13, wherein the plurality of public entities comprise at least one of a web site, an article, a blog, and a user on a social networking site.

16. The system of claim 13, wherein the encoded information about the corresponding public entity comprises relevancy values corresponding to a plurality of keywords, each of the relevancy values representing relevancy of the corresponding public entity to each keyword.

17. The system of claim 13, wherein the user information comprises at least one of a search history of the user, web page access history of the user, and web page bookmarks of the user.

18. The system of claim 13, wherein the encoded user information comprises relevancy values corresponding to a plurality of keywords, each of the relevancy values representing relevancy of the user information to each keyword.

19. The system of claim 13, wherein the select server fingerprints are selected from server fingerprints based on popularity of the corresponding public entity.

20. A machine-readable storage medium comprising machine-readable instructions for causing a processor to execute a method for anonymously recommending public entities, the method comprising:

generating server fingerprints corresponding to a plurality of public entities, each server fingerprint comprising relevancy values corresponding to a predetermined number of predetermined keywords, each of the relevancy values representing relevancy of a corresponding public entity to each predetermined keyword;

selecting, from the generated server fingerprints, select server fingerprints to communicate to a client based on popularity of the corresponding public entity; and

communicating the select server fingerprints to the client;

wherein a user fingerprint is generated based on user information associated with a user, the user fingerprint comprising relevancy values corresponding to a plurality of keywords, each of the relevancy values representing relevancy of the user information to each keyword,

wherein the user fingerprint is compared with the select server fingerprints to select a server fingerprint for recommendation, and

wherein a recommendation of a public entity corresponding to the server fingerprint for recommendation is generated.