Dynamic Pre-Filter for Private Physical-Browsing Advertising Inference
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing targeted advertising technologies fail to leverage physical browsing data effectively while ensuring user privacy, as this data is sensitive and often contains private information.
Innovation Solution
Deploying a pre-filter on user devices to process physical browsing data locally, making inferences compliant with user privacy policies, and transmitting only relevant information to advertisers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If physical browsing data is collected and transmitted to advertisers, then advertising targeting effectiveness is improved, but user privacy is compromised
Solution Approach 1:
A privacy-preserving computation system acts as an intermediary between users and advertisers, enabling targeted advertising without direct access to raw physical browsing data. The system uses secure multi-party computation and homomorphic encryption to allow advertisers to receive aggregated inference results (e.g., shopping behavior patterns) without exposing individual user data, thus resolving the contradiction between advertising effectiveness and privacy protection
Solution Approach 2:
The system extracts only the necessary advertising-relevant information from physical browsing data through local processing on user devices. Inference engines on mobile devices process raw sensor data locally and transmit only aggregated results to advertisers, removing unnecessary personal identifiers and sensitive details while retaining advertising value
2Object-affected harmful factors
If physical browsing data is processed locally on user devices, then user privacy is protected, but data utility for advertising is reduced
Solution Approach 1:
The system performs preliminary processing of physical browsing data on user devices before transmission. Local inference engines pre-compute behavior patterns and aggregate data locally, preparing it in an advertising-ready format that preserves utility while removing privacy risks. This preliminary action ensures data is optimized for advertising purposes before leaving the user device
Solution Approach 2:
The system transforms raw physical browsing data into different parameter representations suitable for advertising. Local processing converts detailed sensor data into aggregated behavioral metrics and inference results with different statistical properties, maintaining advertising relevance while fundamentally changing the data format to protect privacy
3Measurement precision
If comprehensive physical browsing data is collected, then advertising accuracy is improved, but system complexity increases
Solution Approach 1:
The system segments the advertising data collection and processing function across multiple components: local inference engines on user devices, privacy-preserving computation servers, and advertiser analysis systems. Each segment handles specific tasks, distributing complexity rather than concentrating it in a single centralized system, thereby managing overall system complexity while maintaining advertising accuracy
Data Source
AI summary
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.