Search Request Processing With Anonymized User Embeddings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing search methodologies compromise user privacy and efficiency by requiring the sharing of sensitive personal data or manual input to provide personalized content, and anonymization methods may not ensure adequate security or accuracy.
Innovation Solution
A content provision system utilizing user data embedding and content determination machine-learning models to generate anonymized and compressed user profiles, allowing secure and efficient personalized content retrieval without sharing sensitive data, by using user data embedding (UDE) and content determination (CD) machine-learning models to process content retrieval requests.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensitive personal data is shared with external servers to provide personalized content, then personalization accuracy is improved, but user privacy and security are compromised
Solution Approach 1:
The patent extracts only the essential features needed for personalization by creating anonymized user profiles that contain aggregated statistical data rather than raw personal information. This allows the system to achieve personalization accuracy while removing harmful personal data elements before sharing with external servers.
Solution Approach 2:
The patent introduces anonymized user profiles as an intermediary between raw personal data and external servers. These profiles act as a mediator that preserves personalization capabilities while blocking direct exposure of sensitive information, thus resolving the contradiction between accuracy and privacy.
2Object-affected harmful factors
If anonymization is applied to personal data before transmission, then user privacy is protected, but personalization accuracy may be reduced
Solution Approach 1:
The patent transforms personal data by changing its parameters through aggregation and statistical summarization. Instead of removing all personal characteristics, it transforms them into anonymized profiles that retain sufficient information for personalization while meeting security requirements through parameter modification.
Solution Approach 2:
The patent applies different levels of anonymization to different data elements within user profiles. Sensitive fields are heavily anonymized or removed, while less sensitive fields retain more detail, allowing the system to balance privacy protection with personalization accuracy on a field-by-field basis.
3Object-affected harmful factors
If traditional methods like cookies or manual input are used for personalization, then user privacy is maintained, but efficiency and user experience are reduced
Solution Approach 1:
The patent performs preliminary anonymization and aggregation of user data automatically in the background before any user interaction. This preliminary action creates ready-to-use anonymized profiles that enable immediate personalization without requiring users to manually input preferences or undergo multiple search iterations, thus maintaining privacy while improving efficiency.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Method, systems and computer programs for content provision are provided. A requestor node generates an anonymized and compressed representation of the user profile using a user data embedding machine-learning model inputting user data of a user profile. The content retrieval platform receives the anonymized and compressed representation of the user profile and a content retrieval request and inputs the anonymized and compressed representation of the user profile and the content retrieval request to a content determination machine-learning model to determine content in response to the content retrieval request.