Audience Selection via Depersonalized Keywords
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is a growing concern about the collection and use of online consumption history for marketing and content customization, which raises privacy issues as it involves the storage and analysis of sensitive information about users' browsing habits.
Innovation Solution
The system uses depersonalized keywords to characterize content accessed by users, allowing for the recording of consumption history without storing specific content descriptors like URLs, thereby protecting user privacy while still enabling analysis for marketing and content customization purposes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If content descriptors (URLs, domain names) are stored to identify accessed content, then measurement precision and behavioral analysis capability are improved, but user privacy is compromised and sensitivity of stored information increases
Solution Approach 1:
The patent extracts only the essential identifying features (keywords) from the full content descriptors (URLs, domain names). Instead of storing complete URLs that uniquely identify specific content locations, the system extracts and stores only depersonalized keywords that characterize the content topic, thereby reducing privacy intrusion while preserving behavioral analysis capability
Solution Approach 2:
The patent uses temporary, disposable content descriptors during the measurement process that are subsequently discarded. Full URLs and domain names are used transiently for tracking purposes but are not retained in the consumption history, replacing them with less sensitive keyword representations that can be safely stored long-term
2Adaptability or versatility
If detailed consumption history is recorded for marketing and content customization, then ad targeting accuracy and content personalization are improved, but information sensitivity and privacy risk increase
Solution Approach 1:
The system extracts only the necessary identifying characteristics (keywords) from detailed content descriptors. By removing sensitive identifying information like full URLs while retaining topical keywords, the system maintains marketing effectiveness for ad targeting and content personalization while reducing the privacy risk associated with storing detailed browsing history
Solution Approach 2:
The patent transforms the representation of consumption history from detailed parameters (full URLs, domain names, complete page paths) to simplified parameters (depersonalized keywords). This parameter transformation maintains the ability to perform marketing analysis and content customization while significantly reducing the sensitivity and privacy risk of the stored information
Data Source
AI summary
An audience selection system for the selection of an entity, based on an entity's consumption history without requiring the storage of a content descriptor for identifying content previously accessed by the entity. By directly and/or indirectly observing the usage of words used to locate content through a search engine over time for a population, a list of depersonalized keywords can be discovered, creating the ability to characterize content based on depersonalized keywords. A protected consumption history can be recorded for an entity using depersonalized keywords instead of recording a content descriptor for identifying the content. Depersonalized keywords do not uniquely identify content. Associating depersonalized keywords with an entity does not mean that the entity has used those depersonalized keywords; it only means that the entity has accessed content which has been accessed in the past by other entities in a population using the depersonalized keywords.