Recommendations based on private data using a dynamically deployed pre-filter
Methods and systems for targeted advertisement include transmitting a pre-filter to a user device, responsive to contextual information supplied by the user device to determine one or more inferences based on physical browsing information, collected at the user device, in compliance with one or more privacy policies of the user. One or more targeted advertisements are determined, using a processor, based on the one or more inferences. The one or more targeted advertisements are transmitted to the user device.
1. A method for targeted advertisement, comprising:
receiving contextual information from a user device;
transmitting a pre-filter to the user device, responsive to the contextual information, to determine one or more inferences based on physical browsing information, collected at the user device, in compliance with one or more privacy policies of the user;
receiving the one or more inferences determined by the pre-filter from the user device;
determining, using a processor, one or more targeted advertisements based on the one or more inferences; and
transmitting the one or more targeted advertisements to the user device.
2. The method of claim 1 , wherein the contextual information comprises one or more pieces of information regarding the user's location and a type of data collected by the user device that is permitted by the privacy policies of the user.
3. The method of claim 1 , wherein the contextual information identifies one or more types of physical browsing information collected at the user device and the pre-filter for transmission is selected in accordance with a corresponding type of physical browsing information.
4. The method of claim 1 , wherein the one or more inferences comprise analysis outputs based on the physical browsing information and do not include the physical browsing information itself.
5. A method for targeted advertisement, comprising:
transmitting a context for a user device to an advertisement provider;
receiving a pre-filter from an advertisement provider responsive to the transmitted context;
determining one or more inferences using a processor by applying the pre-filter to collected physical browsing information, collected at the user device, in accordance with one or more privacy policies of a user;
transmitting the one or more inferences to the advertisement provider;
receiving one or more targeted advertisements from the advertisement provider in response to the one or more inferences; and
displaying the one or more targeted advertisements at the user device.
6. The method of claim 5 , wherein the contextual information comprises one or more pieces of information regarding the user's location and a type of data collected by the user device that is permitted by the privacy policies of the user.
7. The method of claim 5 , wherein the contextual information identifies one or more types of physical browsing information collected at the user device and the pre-filter corresponds to a type of physical browsing information.
8. The method of claim 5 , wherein the one or more inferences comprise analysis outputs based on the physical browsing information and do not include the physical browsing information itself.
9. A system for targeted advertisement, comprising:
a server pre-filter module configured to receive contextual information from a user device, to transmit a pre-filter to the user device, responsive to the contextual information, to determine one or more inferences based on physical browsing information, collected at the user device, in compliance with one or more privacy policies of the user, and to receive the one or more inferences determined by the pre-filter from the user device;
a recommendation module comprising a processor configured to determine one or more targeted advertisements based on the one or more inferences; and
an advertisement module configured to transmit the one or more targeted advertisements to the user device.
10. The system of claim 9 , wherein the contextual information comprises one or pieces of information regarding the user's location and a type of data collected by the user device that is permitted by the privacy policies of the user.
11. The system of claim 9 , wherein the contextual information identifies one or more types of physical browsing information collected at the user device and the pre-filter for transmission is selected in accordance with a corresponding type of physical browsing information.
12. The system of claim 9 , wherein the one or more inferences comprise analysis outputs based on the physical browsing information and do not include the physical browsing information itself.
13. The system of claim 9 , wherein the physical browsing information comprises image data collected by one or more cameras at the user device.
14. A system for targeted advertisement, comprising:
a client pre-filter module comprising a processor configured to transmit a context for a user device to an advertisement provider, to receive a pre-filter from an advertisement provider responsive to the transmitted context, to determine one or more inferences by applying the pre-filter to collected physical browsing information, collected at the user device, in accordance with one or more privacy policies of a user, and to transmit the one or more inferences to an advertisement provider; and
an advertisement module configured to receive one or more targeted advertisements from the advertisement provider in response to the one or more inferences and to display the one or more targeted advertisements at the user device.
15. The system of claim 14 , wherein the contextual information comprises one or more pieces of information regarding the user's location and a type of data collected by the user device that is permitted by the privacy policies of the user.
16. The system of claim 14 , wherein the contextual information identifies one or more types of physical browsing information collected at the user device and the pre-filter corresponds to a type of physical browsing information.
17. The system of claim 14 , wherein the one or more inferences comprise analysis outputs based on the physical browsing information and do not include the physical browsing information itself.
18. The system of claim 14 , wherein the physical browsing information comprises image data collected by one or more cameras at the user device.
19. The method of claim 1 , wherein the pre-filter processes private user information that is protected by the one or more privacy policies to determine the one or more inferences and wherein the one or more inferences do not themselves include the private user information.
20. The method of claim 5 , wherein the pre-filter processes private user information that is protected by the one or more privacy policies to determine the one or more inferences and wherein transmitting the one or more inferences does not include transmitting the private user information.