Feature-Value Attachment for Ad Relevance and Fraud Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current advertisement systems require users to perform excessive work to find relevant information, leading to high click rates with little user intent for conversion, resulting in advertisers paying for clicks with no benefit, due to limited ad presentation and lack of contextual information.
Innovation Solution
Attaching structured information as feature-value pairs to advertisements, allowing users to sort and filter based on relevant criteria, and enabling hybrid pricing models by associating these pairs with advertisements for improved relevance and fraud detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If advertisements are restricted to small presentation areas with limited information, then ad delivery efficiency is improved, but user ability to determine product relevance deteriorates
Solution Approach 1:
The patent segments advertisement information into two parts: essential information (title, short description, URL) displayed in the limited ad space, and detailed structured information (feature-value pairs) stored separately and accessible through user interaction. This segmentation allows efficient ad delivery while preserving complete product information for users who need it.
Solution Approach 2:
The patent adds a new dimension to advertisement presentation by incorporating sortable and filterable feature-value pairs alongside the traditional ad display. This transforms the ad presentation from a static, information-limited format to a dynamic, multi-dimensional interface where users can explore product details without leaving the ad context.
2Loss of information
If users must select multiple advertisements and navigate to landing pages to find relevant information, then information completeness is improved, but user time and effort deteriorates
Solution Approach 1:
The patent performs preliminary action by pre-structuring and displaying key product features directly in the advertisement presentation. Users can view sorted and filtered product information without having to navigate to landing pages, completing their information search within the ad context itself.
Solution Approach 2:
The patent introduces an intermediary layer between the advertisement and the landing page - the structured feature-value pairs with sorting and filtering capabilities. This intermediary provides users with comprehensive product information directly in the ad presentation, eliminating the need to navigate to landing pages while still allowing access to full details when needed.
3Device complexity
If advertisements present minimal information, then ad system complexity is reduced, but user satisfaction with ad relevance deteriorates
Solution Approach 1:
The patent implements self-service by enabling users to sort and filter advertisements based on their own criteria using the structured feature-value pairs. Users can independently organize and find relevant ads without requiring complex system interventions, improving satisfaction while maintaining system efficiency.
4Quantity of substance
If advertisers pay per click without conversion intent, then advertisement delivery volume is improved, but advertiser return on investment deteriorates
Solution Approach 1:
The patent implements feedback by providing users with sorted and filtered advertisement information that helps them make informed decisions about product relevance. This feedback loop reduces wasted clicks on irrelevant ads and improves the quality of clicks that do occur, thereby improving advertiser ROI while maintaining healthy click volumes.
Data Source
AI summary
An approach is provided for associating structured information as feature-value pairs with advertisements at an advertisement system that provides advertisements for presentation with primary content. Feature-value pairs corresponding with advertisements describe features of the products or services associated with the advertisements. The feature-value pairs may be used by the advertisement system in a number of different manners, including, among other things: using the feature-value pairs during selection of advertisements for presentation with primary content: allowing users to sort and/or filter advertisements during presentation with primary content based on the associated feature-value pairs; exposing additional information with the advertisements; facilitating fraud detection for the advertisement system; and enabling a hybrid pricing model.


