Dynamic Relevancy Scoring for Ad Targeting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing digital advertising systems face challenges in ensuring ad relevancy, often trading off accuracy and precision for execution speed, which affects customer experience and advertising yield.
Innovation Solution
The system introduces a dynamic relevancy scoring mechanism that allows customers to finely tune ad selection by setting relevancy scores, using customer input and contextual knowledge, and enables ad-hoc property filtering and selection, incorporating per-attribute values and per-ID relevancy calculations to enhance ad targeting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If traditional relevancy calculation approaches are used, then execution speed is improved, but accuracy and precision of ad relevancy deteriorate
Solution Approach 1:
The patent implements dynamic relevancy scoring that adjusts weights and parameters in real-time based on contextual knowledge and customer input. The system dynamically modifies relevancy calculations during ad selection rather than using static pre-computed scores, allowing it to maintain high accuracy while adapting to changing contexts and customer preferences.
Solution Approach 2:
The system changes multiple parameters simultaneously including relevancy weights, filtering thresholds, and scoring algorithms based on contextual inputs. By dynamically adjusting these parameters rather than fixing them beforehand, the system achieves both speed and accuracy in relevancy determination.
2Manufacturing precision
If detailed relevancy calculations are performed, then ad targeting precision is improved, but system complexity increases
Solution Approach 1:
The patent segments the relevancy calculation into distinct modular components: contextual knowledge processing, customer input analysis, dynamic weight assignment, and scoring algorithms. Each module handles a specific aspect of relevancy determination, making the complex system more manageable and maintainable while preserving high targeting precision.
Solution Approach 2:
The system introduces contextual knowledge as an intermediary layer between raw ad data and final relevancy scores. This intermediary processes and structures information before it enters the scoring mechanism, simplifying the overall complexity while enhancing targeting precision through enriched contextual understanding.
3Measurement precision
If dynamic relevancy scoring with customer input is implemented, then ad selection accuracy is improved, but processing time increases
Solution Approach 1:
The system performs preliminary processing of contextual knowledge and customer preferences before actual ad selection occurs. By pre-processing and structuring this information in advance, the system reduces the computational burden during real-time ad selection, maintaining high accuracy while minimizing additional processing time.
Solution Approach 2:
The patent implements optimized calculation pathways that skip unnecessary computational steps when contextual information is already available or when certain conditions are met. This allows the system to rush through the relevancy calculation for straightforward cases while still performing detailed analysis when needed, balancing accuracy with processing speed.
Data Source
AI summary
This document presents a system and method for improving advertising targeting through the use of a Relevancy Score for clients accessing a marketplace. The improved technology may combine advertiser information from those businesses participating in a marketplace with client request information. The improvement defines and selects ads and ad-campaigns based upon how relevant the ads or ad-campaigns selected are for the customers to be targeted to view ads from the client. The Relevancy Score may be based upon ad attributes and weights of the attributes, or may be supplied by a client to optimize the selection and presentation of ads or ad-campaigns to a client that meet or exceed a Relevancy Score prepared or provided to the system.