Dynamic Ad Targeting via Scroll and Eye Fixation Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing targeted marketing techniques fail to accurately identify a user's current state of mind, leading to the presentation of advertisements that are not immediately relevant, resulting in reduced click-through rates due to their lack of alignment with the user's current interests.
Innovation Solution
A methodology for dynamically varying recommended marketing content in real-time based on the user's current interactions with web page content, such as scroll position and eye fixation, to identify which portions of the content are being read or skimmed, and generating keywords for presenting relevant advertisements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional targeted advertising uses cookies to generate user profiles based on browsing history, then ads can be targeted to user interests, but the ads appear only during subsequent visits which may occur hours, days or months later, reducing immediate relevance and click-through rates
Solution Approach 1:
The system performs preliminary analysis of the web page content structure and identifies relevant advertising opportunities before the user completes their browsing session. By pre-processing the content to extract topics and determine ad placements, the system prepares targeted ads in advance, enabling immediate presentation during subsequent visits without the hours, days, or months delay of traditional cookie-based profiling.
Solution Approach 2:
The patent introduces an intermediary analysis layer between the web page content and the advertising system. This intermediary process analyzes the actual content being viewed (not just browsing history) and generates topic-based ad recommendations that can be immediately served, bridging the gap between user current interests and ad delivery timing.
2Adaptability or versatility
If ads are targeted based on entire web page content, then advertising can be related to the subject matter, but the system cannot identify which specific portions of content the user is currently reading, reducing precision of targeting
Solution Approach 1:
The system segments the web page content into distinct topical sections or regions and analyzes each segment separately. This segmentation allows the system to identify which specific portion of the content the user is currently reading and to match ads to that specific segment's topic, rather than treating the entire page as a single subject matter block.
Solution Approach 2:
The patent applies local quality by making advertising content specific to particular regions or sections of the web page rather than applying a single ad strategy to the entire page. Each content segment receives customized ad targeting based on its specific topic, improving precision by matching ads to the local context of what the user is actually reading.
Data Source
AI summary
Techniques are disclosed for presenting recommended marketing content that can be dynamically varied (e.g., in real time or near-real time) based on the particular content of a web page that a user is currently reading, the content that the user has previously read, or a combination of these factors. For example, the current interactions of a user with content of a web page, such as scroll position or eye fixation, can be used to identify which portion or portions of the web page content the user is currently reading and which portions of the web page content the user is skimming or skipping over. Keywords can then be generated based on the content in those portions of the web page that the user is currently reading. Next, recommended marketing content corresponding to the keywords can be retrieved and presented to the user.