Cross-Screen Ad Placement Using Deduplicated Consumer Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing advertising strategies struggle to efficiently optimize video advertising across multiple devices due to fragmented consumer data, manual analytical processes, and the inability to integrate disparate data sources, leading to inefficient slot selection and delayed responses to market trends.
Innovation Solution
A system and method that integrates consumer data from multiple devices using probabilistic and deterministic methods to create look-alike models, predicting future consumption behavior, and optimizing advertising campaigns across TV and mobile devices, while considering hard and soft constraints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analytical processes are used for advertising optimization, then human expertise can be applied to strategy development, but the process is time-consuming and cannot respond quickly to market trends
Solution Approach 1:
The patent replaces manual analytical processes with automated computer-based systems that use algorithms to analyze consumer data and optimize advertising campaigns. This substitution eliminates the time-consuming nature of manual analysis while maintaining or improving the precision of advertising strategy through systematic data processing and modeling capabilities.
Solution Approach 2:
The system enables self-service advertising optimization by automatically analyzing consumer data, generating look-alike models, and recommending campaign strategies without requiring continuous human intervention. The automated processes continuously adapt to market changes and optimize advertising placement in real-time, freeing human analysts from routine analytical tasks.
2Adaptability or versatility
If consumer data from multiple devices is integrated using probabilistic and deterministic methods, then look-alike models can be created to predict future consumption behavior, but the system complexity increases
Solution Approach 1:
The patent segments consumer data into distinct categories (probabilistic data and deterministic data) from different devices, allowing each type to be processed using appropriate methods. This segmentation enables the system to handle complex multi-device data integration by breaking it down into manageable segments that can be analyzed and combined systematically to create accurate look-alike models.
Solution Approach 2:
The system introduces intermediary processing layers that mediate between raw multi-device consumer data and the look-alike model generation. These intermediaries include data normalization processes, probability calculation engines, and model validation mechanisms that simplify the integration complexity while enabling sophisticated consumer behavior prediction capabilities.
3Productivity
If advertising content is allocated efficiently across multiple devices, then yield is improved and costs are reduced, but the ability to manage constraints becomes more difficult
Solution Approach 1:
The patent implements dynamic constraint management that automatically adjusts advertising allocation across devices based on real-time conditions and constraints. The system dynamically optimizes yield by continuously evaluating hard and soft constraints and adapting the advertising strategy accordingly, enabling efficient multi-device allocation while managing constraint complexity through automated dynamic adjustment rather than static rule-based approaches.
4Ease of operation
If existing advertising software tools are used for constraint exploration, then simple relational database exploration is possible, but they cannot process analytics and produce placement suggestions
Solution Approach 1:
The patent merges previously separate functions into a unified advertising optimization system. It combines constraint exploration capabilities with advanced analytics processing and automated placement suggestion generation in a single integrated platform. This merging eliminates the gap between simple database exploration and sophisticated optimization, allowing the system to simultaneously explore constraints, analyze consumer data, and generate actionable placement recommendations.
Data Source
AI summary
A method may include obtaining an advertising campaign, determining one or more devices associated with a consumer, and associating the one or more devices with a consumer identifier. The method also includes obtaining data associated with the one or more devices associated and corresponding the data with the consumer identifier. The method also includes deduplicating the data related to the consumer identifier across one or more viewing methods. The method also includes displaying the deduplicated data. The method also includes adjusting the advertising campaign based on user input.