Query Statistics Engine for Privacy-Safe Ad Targeting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current advertisement selection and display systems lack efficient methods to identify and categorize search queries that are relevant to advertisers while ensuring user privacy, particularly in filtering out personal information and providing actionable insights for improving ad campaigns.
Innovation Solution
A computer-implemented method and apparatus that processes search queries from a search query log, identifying and categorizing queries based on similarity to advertisement keywords, while ensuring a low probability of personal information inclusion, using a query statistics engine to normalize and match queries with exact, expanded, or broad matches, and providing privacy-safe queries to advertisers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If search queries are provided to advertisers to improve ad campaigns, then advertisement performance can be improved, but user privacy may be compromised due to inclusion of personal information
Solution Approach 1:
The patent extracts and removes personal information from search queries before providing them to advertisers. The system identifies and filters out queries containing personal identifiers (emails, phone numbers, addresses) while retaining anonymized query data that still provides actionable insights for ad optimization without exposing user privacy.
Solution Approach 2:
The patent introduces an intermediary processing layer between the search query log and advertisers. This intermediary system anonymizes queries by removing personal information while preserving the essential search intent and categorization data, acting as a mediator that protects user privacy while still enabling advertisers to gain insights.
2Loss of information
If all search queries are provided to advertisers, then complete information is available for analysis, but data processing complexity and time increase
Solution Approach 1:
The patent segments search queries into different categories (e.g., informational, navigational, transactional) and filters them based on relevance to advertisement keywords. This segmentation approach allows the system to process and provide only the most relevant queries to advertisers, reducing overall processing complexity while maintaining information completeness for targeted analysis.
Solution Approach 2:
The patent performs preliminary filtering and categorization of search queries before providing them to advertisers. By pre-processing queries to identify and remove personal information and categorize by relevance, the system reduces the complexity of subsequent analysis while ensuring that complete and relevant information is available when needed.
3Measurement precision
If personal information is included in search queries provided to advertisers, then query accuracy is maintained, but user privacy and security are compromised
Solution Approach 1:
The patent systematically extracts and removes personal information elements (email addresses, phone numbers, physical addresses, social security numbers) from search queries while preserving the core search intent and keywords. This extraction process maintains query accuracy for advertising purposes while eliminating privacy risks associated with personal information exposure.
Data Source
AI summary
A system to provide search query information. The system receives a request for search query information, identifies a set of search queries from a search query log that includes search queries submitted to a search service over a predetermined length of time, and provides the set of search queries. Each of the set of search queries is associated with at least a predetermined number of unique identifiers. Each of the set of search queries is matched to the request for search query information by a combination of exact matches, expanded matches, and broad matches.