Recommendation system for protecting user privacy

Patent metadata

Field	Value
Publication number	US-9530024-B2
Application number	US-201414333063-A
Country	US
Kind code	B2
Filing date	Jul 16, 2014
Priority date	Jul 16, 2014
Publication date	Dec 27, 2016
Grant date	Dec 27, 2016

Abstract

One embodiment of the present invention sets forth a technique for providing application command recommendations to a privacy-sensitive client device. The technique includes receiving a command log from each general client device included in a plurality of general client devices and analyzing the command logs to generate a command recommendation file. The command recommendation file may indicate a relationship between one or more application commands executed by at least one of the general client devices and one or more application commands that are available for execution by the privacy-sensitive client device. The technique further includes transmitting the command recommendation file to the privacy-sensitive client device.

First claim

What is claimed is:

1. A computer-implemented method for providing application command recommendations to a privacy-sensitive client device, the method comprising:
receiving a command log from each general client device included in a plurality of general client devices;
analyzing the command logs to generate a command recommendation file, wherein the command recommendation file indicates a relationship between one or more application commands executed by at least one of the general client devices and one or more application commands that are available for execution by the privacy-sensitive client device, wherein the privacy-sensitive client does not share command log information associated with the one or more application commands executed by the at least one general client device; and
transmitting the command recommendation file to the privacy-sensitive client device.

2. The method of claim 1 , wherein the command recommendation file comprises a plurality of ratings, and each rating indicates a relationship between two or more application commands executed by at least one of the general client devices.

3. The method of claim 1 , wherein the command recommendation file comprises a command similarity matrix having a plurality of entries, and each entry included in the plurality of entries stores a rating indicating the similarity between two or more application commands.

4. The method of claim 1 , further comprising generating the command recommendation file based on the command logs received from the plurality of general client devices.

5. The method of claim 4 , wherein generating the command recommendation file is performed based on an inverse user-frequency rating function.

6. The method of claim 1 , further comprising:
receiving an updated command log from one or more general client devices;
analyzing the one or more updated command logs to generate an updated command recommendation file; and
transmitting the updated command recommendation file to the privacy-sensitive client device.

7. The method of claim 1 , wherein the one or more application commands executed by the at least one general client device comprise digital content selections.

8. A non-transitory computer-readable storage medium including instructions that, when executed by a processor, cause the processor to provide recommended software application commands to a client device, by performing the steps of:
receiving a command log from each general client device included in a plurality of general client devices;
analyzing the command logs to generate a command recommendation file, wherein the command recommendation file indicates a relationship between one or more application commands executed by at least one of the general client devices and one or more application commands that are available for execution by the privacy-sensitive client device, wherein the privacy-sensitive client does not share command loci information associated with the one or more application commands executed by the at least one general client device; and
transmitting the command recommendation file to the privacy-sensitive client device.

9. The non-transitory computer-readable storage medium of claim 8 , wherein the command recommendation file comprises a plurality of ratings, and each rating indicates a relationship between two or more application commands executed by at least one of the general client devices.

10. The non-transitory computer-readable storage medium of claim 8 , wherein the command recommendation file comprises a command similarity matrix having a plurality of entries, and each entry included in the plurality of entries stores a rating indicating the similarity between two or more application commands.

11. The non-transitory computer-readable storage medium of claim 8 , further comprising generating the command recommendation file based on the command logs received from the plurality of general client devices.

12. The non-transitory computer-readable storage medium of claim 11 , wherein generating the command recommendation file is performed based on an inverse user-frequency rating function.

13. The non-transitory computer-readable storage medium of claim 8 , further comprising:
receiving an updated command log from one or more general client devices;
analyzing the one or more updated command logs to generate an updated command recommendation file; and
transmitting the updated command recommendation file to the privacy-sensitive client device.

14. The non-transitory computer-readable storage medium of claim 8 , wherein the one or more application commands executed by the at least one general client device comprise digital content selections.

15. The non-transitory computer-readable storage medium of claim 8 , wherein the privacy-sensitive client device does not share any command logs.

16. A computer-implemented method for providing application command recommendations to a privacy-sensitive client device, the method comprising:
receiving a command recommendation file from a server, wherein the command recommendation file indicates a relationship between one or more application commands executed by at least one general client device and one or more application commands that are available for execution by the privacy-sensitive client device, wherein the privacy-sensitive client does not share command loci information associated with the one or more application commands executed by the at least one general client device;
determining one or more application commands executed by the privacy-sensitive device; and
generating one or more application command recommendations based on the one or more application commands executed by the privacy-sensitive device.

17. The method of claim 16 , wherein the privacy-sensitive client device accesses the command recommendation file and generates the one or more application command recommendations while the privacy-sensitive client device is offline.

18. The method of claim 16 , wherein the command recommendation file comprises a plurality of ratings, each rating indicating a relationship between two or more application commands executed by a plurality of general client devices that includes the at least one general client device.

19. The method of claim 16 , wherein the command recommendation file comprises a command similarity matrix having a plurality of entries, and each entry included in the plurality of entries stores a rating indicating the similarity between two or more application commands.

20. The method of claim 19 , wherein one or more of the ratings are based on an inverse user-frequency rating.

21. The method of claim 16 , wherein the one or more application commands executed by the at least one general client device comprise digital content selections.

22. The method of claim 16 , wherein the one or more application command recommendations are generated without transmitting any command logs from the privacy-sensitive client device to the server.

Assignees

• Autodesk Inc

Inventors

• Li Wei
• Matejka Justin Frank
• Grossman Tovi
• Fitzmaurice George

Classifications

• H04L63/0407 Primary

  wherein the identity of one or more communicating identities is hidden (cryptographic mechanisms or cryptographic arrangements for anonymous credentials or for identity based cryptographic systems H04L9/00) · CPC title

• G06F21/6245 Primary

  Protecting personal data, e.g. for financial or medical purposes · CPC title

• H04W12/02

  Protecting privacy or anonymity, e.g. protecting personally identifiable information [PII] · CPC title