Uncertain User Data for Privacy-Preserving Ad Targeting

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Digital advertising faces a challenge in providing targeted advertisements while maintaining user privacy, as existing methods often compromise personal information, leading to consumer reluctance in sharing data.

Innovation Solution

The system generates uncertain user data by combining actual user data with noise data, allowing for targeted advertisements to be delivered without revealing sensitive information, by using conditional ad objects that are verified using actual user data, ensuring privacy protection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If user data is shared to enable targeted advertising, then advertising effectiveness is improved, but user privacy is compromised

Engineering Contradiction:

Improveadvertising effectivenessVSAvoiduser privacy compromise

Core Design Contradiction:

ProductivityVSObject-affected harmful factors

Solution Approach 1:

The system creates a synthetic copy of user data (uncertain user data) that resembles actual user data but contains added noise and inaccuracies. This copy is used for advertising targeting while the real user data remains private and undisclosed to advertisers, resolving the contradiction between advertising effectiveness and privacy protection

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The uncertain user data acts as an intermediary between the user's actual private data and the advertising system. It allows the advertising system to perform targeting functions without direct access to or knowledge of the user's true personal information, thus mediating between advertising effectiveness and privacy concerns

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If actual user data is used for advertising targeting, then ad relevance is improved, but user trust is reduced

Engineering Contradiction:

Improvead relevanceVSAvoiduser trust

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The system uses a synthetic copy of user data (uncertain user data) instead of actual user data for advertising targeting. This copy maintains enough similarity to provide relevant ads while being fundamentally different from the real data, thereby preserving user trust while maintaining ad relevance

Inventive Principle:

Principle #26Copying

Solution Approach 2:

Instead of giving advertisers direct access to actual user data, the system inverts the approach by providing them with deliberately inaccurate synthetic data. This inversion allows advertisers to perform targeting functions while the user maintains control and trust over their actual private information

Inventive Principle:

Principle #13The other way round (Inversion)

Data Source

PatentUS10430830B2Advertisement selection using uncertain user data

Publication Date: 2019.10.01 SAMSUNG ELECTRONICS CO LTD

AI summary

A method and system are disclosed. The method includes generating uncertain user data corresponding to a user of the user device and transmitting the uncertain user data to a remote computing device. The uncertain user data includes a combination of actual user data and noise data. The method includes receiving an advertisement response message from the remote computing device that includes a plurality of conditional ad objects, each conditional ad object including ad content, one or more access mechanisms, and one or more conditions. The method further includes selecting one or more of the plurality of conditional ad objects based on the actual user data and the one or more conditions defined in the selected conditional ad objects. Furthermore, the method includes displaying, for each selected conditional ad object, an advertisement that is based on the ad content and at least one access mechanism defined in the conditional ad object.