Context-Aware Ad Selection Using Deep Neural Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The ineffectiveness of online advertisements is exacerbated by the presentation of unrelated and irrelevant ads, which can diminish user engagement and value.
Innovation Solution
The use of deep neural networks with two independent components to process general quality and local contextual information to determine advertisement relevance scores, ensuring more relevant ads are presented based on surrounding content, and their positioning within user interfaces.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If advertisements are presented ubiquitously across online content, then advertisement coverage and visibility are improved, but advertisement relevance and user engagement deteriorate
Solution Approach 1:
The patent applies local quality by analyzing the contextual information surrounding each advertisement placement location and selecting ads that are relevant to that specific local context. Instead of uniform ad placement, the system evaluates nearby content (articles, videos, products) and chooses ads that match the local theme, thereby improving relevance while maintaining coverage.
Solution Approach 2:
The system changes the selection parameters from purely random or position-based ad placement to context-aware selection. By incorporating parameters such as content category, user behavior patterns, and surrounding context into the ad selection algorithm, the system optimizes the balance between coverage and relevance.
2Quantity of substance
If unrelated advertisements are presented, then advertisement volume is maintained, but user engagement and value deteriorate
Solution Approach 1:
The patent employs feedback mechanisms by continuously monitoring user interactions with advertisements and adjusting the selection model accordingly. User behavior data (clicks, views, time spent) is fed back into the system to refine future ad selections, ensuring that high-engagement ads are prioritized while maintaining adequate volume.
Solution Approach 2:
The system dynamically adjusts selection parameters based on performance metrics. By changing parameters such as ad selection criteria and weighting factors based on real-time engagement data, the system maintains optimal advertisement volume while improving user engagement through more relevant placements.
Data Source
AI summary
Described are systems and methods to determine advertisements to be presented to a user. To determine the advertisements to be presented to the user, the described systems and methods utilize localized contextual information to select the advertisements and the relative positioning of the advertisements to be presented, so as to select and present more relevant advertisements based on the content that is surrounding and proximate to the presentation of the selected advertisements.