Recommendations based on private data using a dynamically deployed pre-filter

Patent metadata

Field	Value
Publication number	US-12387238-B2
Application number	US-202318533013-A
Country	US
Kind code	B2
Filing date	Dec 7, 2023
Priority date	Nov 16, 2015
Publication date	Aug 12, 2025
Grant date	Aug 12, 2025

Abstract

A method for targeted advertisement includes transmitting a pre-filter to the user device, responsive to contextual information from a user device, to determine, using a processor, 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. The method also includes receiving one or more inferences determined by the pre-filter from the user device and transmitting one or more targeted advertisements to the user device based on one or more inferences.

First claim

The invention claimed is:

1. A method comprising:
receiving, at a provider system, a request for content to display on a user device, wherein the request indicates a plurality of types of context data stored by the user device, wherein the plurality of types of context data comprises image data captured by a camera of the user device and inertial data captured by an inertial sensor of the user device;
selecting a plurality of pre-filters from a set of pre-filters based on the plurality of types of the context data stored by the user device, wherein each of the plurality of selected pre-filters is a pre-filter for generating one or more inferences from context data, wherein each of the plurality of selected pre-filters comprises computer-executable instructions for execution on the user device to cause the user device to generate one or more inferences based on context data of a corresponding type of context data of the plurality of types of context data;
transmitting the selected plurality of pre-filters to the user device for application to the context data stored by the user device;
receiving, from the user device, a plurality of inferences generated by applying the plurality of selected pre-filters to the context data stored by the user device, wherein the plurality of inferences do not include the context data stored by the user device;
selecting content to display on the user device based on the plurality of received inferences; and
transmitting the selected content to the user device for display.

2. The method of claim 1 , wherein the image data comprises an image captured by a peripheral device associated with the user device.

3. The method of claim 1 , wherein a selected pre-filter of the plurality of selected pre-filters comprises an object recognition pre-filter that recognizes objects depicted by the image data.

4. The method of claim 1 , further comprising:
receiving user preferences for pre-filters from the user device; and
selecting the plurality of pre-filters from the set of pre-filters based on the user preferences.

5. The method of claim 1 , wherein an inference of the plurality of inferences comprises an activity performed by the user.

6. The method of claim 1 , wherein the user device comprises a mobile device.

7. A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations comprising:
receiving, at a provider system, a request for content to display on a user device, wherein the request indicates a plurality of types of context data stored by the user device, wherein the plurality of types of context data comprises image data captured by a camera of the user device and inertial data captured by an inertial sensor of the user device;
selecting a plurality of pre-filters from a set of pre-filters based on the plurality of types of the context data stored by the user device, wherein each of the plurality of selected pre-filters is a pre-filter for generating one or more inferences from context data, wherein each of the plurality of selected pre-filters comprises computer-executable instructions for execution on the user device to cause the user device to generate one or more inferences based on context data of a corresponding type of context data of the plurality of types of context data;
transmitting the selected plurality of pre-filters to the user device for application to the context data stored by the user device;
receiving, from the user device, a plurality of inferences generated by applying the plurality of selected pre-filters to the context data stored by the user device, wherein the plurality of inferences do not include the context data stored by the user device;
selecting content to display on the user device based on the plurality of received inferences; and
transmitting the selected content to the user device for display.

8. The computer-readable medium of claim 7 , wherein the image data comprises an image captured by a peripheral device associated with the user device.

9. The computer-readable medium of claim 7 , wherein a selected pre-filter of the plurality of selected pre-filters comprises an object recognition pre-filter that recognizes objects depicted by the image data.

10. The computer-readable medium of claim 7 , the operations further comprising:
receiving user preferences for pre-filters from the user device; and
selecting the plurality of pre-filters from the set of pre-filters based on the user preferences.

11. The computer-readable medium of claim 7 , wherein an inference of the plurality of inferences comprises an activity performed by the user.

12. The computer-readable medium of claim 7 , wherein the user device comprises a mobile device.

Assignees

• Maplebear Inc

Inventors

• Chakraborty Supriyo
• Grueneberg Keith
• Ko Bongjun
• Makaya Christian
• Ortiz Jorge J
• Rallapalli Swati
• Salonidis Theodoros
• Urgaonkar Rahul
• Verma Dinesh
• Wang Xiping

Classifications

• G06Q30/0255 Primary

  based on user history · CPC title