Audience Sketch Intersection for Privacy-Preserving Measurement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current sketch-based data exchanges do not allow for the measurement of advanced audience segments, such as buyers of specific products or services, due to privacy concerns and limitations in determining demographics from probabilistic data structures.
Innovation Solution
The proposed solution involves generating an exposure sketch and an audience sketch using the same sketch generation logic, intersecting them using a bitwise 'and' operation to determine the reach for advanced audience segments, and reporting this reach to a client device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sketch-based data exchanges are used to preserve privacy, then user-level data privacy is protected, but the ability to measure advanced audience segments is lost
Solution Approach 1:
The patent introduces sketch data structures as an intermediary between raw user-level data and audience measurement requirements. These sketches enable privacy-preserving computation by allowing set operations (intersection, union, difference) to be performed on aggregated data representations rather than individual user records, thus mediating between privacy protection and measurement needs
Solution Approach 2:
The patent transforms the measurement approach by changing parameters from individual user-level attributes to aggregated sketch representations. By converting user data into sketch formats with specific mathematical properties, the system enables new measurement capabilities for advanced audience segments while maintaining privacy through the transformed parameter space
2Measurement precision
If user-level data is shared for advanced audience measurement, then measurement precision is improved, but privacy security is compromised
Solution Approach 1:
Sketch data structures serve as a mediator that enables precise audience segment measurement without exposing user-level data. The sketches allow for accurate computation of audience metrics through mathematical operations while acting as a protective barrier that prevents direct access to sensitive user information
Solution Approach 2:
The patent creates simplified copies of user data in the form of sketch data structures that retain the essential properties needed for measurement but lack the detailed information that would compromise privacy. These copies enable measurement precision while being inherently less sensitive than the original user-level data
Data Source
AI summary
In one example, a computing system of an audience measurement entity (AME) is described. The computing system is configured to perform a set of acts. The set of acts include obtaining an exposure sketch representing individuals exposed to media content, with the exposure sketch generated using sketch generation logic and AME identifiers for the individuals exposed to the media content. The set of acts also includes obtaining an audience sketch representing individuals within an audience segment, with the audience sketch generated using the sketch generation logic and AME identifiers for the individuals within the audience segment. The set of acts further includes intersecting the exposure sketch with the audience sketch using a bitwise “and” operation. The set of acts also includes determining a reach for the audience segment based on the intersecting. And the set of acts includes reporting the reach for the audience segment to a client device.