Client Device PII Processing for Privacy-Preserving Content Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Online services face challenges in maintaining user privacy and compliance with regulations regarding personal identifying information (PII) while providing relevant content to users, as current methods often require storing and processing PII, which can violate privacy concerns.
Innovation Solution
A system where the client device maintains PII locally and requests external content from an online service, with the service identifying potential content items and processing scores without receiving PII, ensuring that no user data is shared or stored by the online service.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If online services store and process personal identifying information (PII) to provide relevant content to users, then content relevance and personalization are improved, but user privacy is violated and regulatory compliance is compromised
Solution Approach 1:
The system divides the content personalization process into two segments: (1) the client device segment that stores and processes PII locally to generate content scores, and (2) the online service segment that receives only anonymized scores without accessing PII. This segmentation allows content relevance to be maintained through personalized scoring while preventing the online service from storing or processing sensitive user data, thus resolving the privacy violation issue.
Solution Approach 2:
The patent introduces an intermediary mechanism where the client device acts as a mediator between the user's PII and the online service's content selection process. The client device locally processes PII to generate content scores and transmits only these anonymized scores to the online service. This intermediary approach enables the online service to provide relevant content based on user preferences without directly accessing or storing PII, thereby maintaining both content relevance and user privacy.
2Adaptability or versatility
If online services process PII to determine content relevance, then content personalization is improved, but data storage requirements and processing complexity increase
Solution Approach 1:
The patent extracts the PII processing function from the online service and relocates it to the client device. The client device performs the complex task of processing PII locally to generate content scores, while the online service only receives and processes the simplified anonymized scores. This extraction reduces the processing complexity and data storage requirements at the online service while maintaining content personalization capabilities through the client device's local processing.
3Adaptability or versatility
If the system shares PII with online services for content selection, then content relevance is improved, but regulatory compliance is violated
Solution Approach 1:
The client device serves as an intermediary that processes PII locally and generates anonymized content scores without sharing the actual PII with the online service. This intermediary mechanism enables the system to maintain content relevance through personalized scoring while ensuring regulatory compliance by preventing any transmission or storage of sensitive user data at the online service, thus meeting privacy protection requirements.
Solution Approach 2:
The patent extracts and removes PII from the data transmission pipeline between the client device and online service. Only anonymized content scores are extracted for transmission, while PII remains isolated at the client device. This extraction approach ensures that no PII is shared with the online service, thereby maintaining regulatory compliance while still enabling content relevance through the anonymized scoring process.
Data Source
AI summary
Systems and methods for obtaining an external content item from an online service for presentation on the client device is presented. On the client device, a condition is detected in the execution context of an executing application, the condition corresponding to the presentation of an external content item by the application. A request is made to the online service for content items. In response, content information is received, where the content information identifies potential content items. According to various embodiments, initial scores are associated with each potential content item in the content information. At the client device, a completed score is generated for each content item according to local information on the client device and the corresponding initial score. An external content item is selected for presentation on the client device from the potential content items according to, at least in part, the completed scores.