Cross-Screen Advertising Placement with Consumer Graph Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing advertising strategies struggle to efficiently integrate and utilize fragmented consumer data across multiple devices, leading to inefficient advertising inventory selection and delayed responses to market trends, as current methods lack the ability to reliably associate devices with precise audiences and predict consumer behavior.
Innovation Solution
A computer-implemented method that combines actual content consumption behavior with consumer graph analysis to optimize advertising campaigns across multiple devices, using probabilistic and deterministic methods to associate devices with consumers, and integrate data from various sources, enabling real-time dynamic bidding and delivery of advertising content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual methods are used for advertising strategy development, then human analysts can guide selection based on static data, but the process becomes inefficient and delays response to market trends
Solution Approach 1:
The patent replaces manual mechanical analysis processes with automated computer-based systems that use algorithms to process consumer data, perform graph analysis, and generate advertising strategies automatically, eliminating the need for manual human analysis and significantly improving efficiency and response time
Solution Approach 2:
The system enables self-service advertising strategy development by automatically processing consumer data, performing device association analysis, and generating optimized advertising campaigns without requiring human analyst intervention, allowing the system to serve itself in developing and executing advertising strategies
2Adaptability or versatility
If separate entities plan for different media platforms, then each platform can be optimized independently, but consumer data remains fragmented and cannot be integrated across devices
Solution Approach 1:
The patent merges previously separate consumer data silos from different media platforms into a unified consumer graph that integrates data across TV, mobile, and online devices, enabling comprehensive cross-platform analysis while maintaining the ability to optimize for each specific platform
Solution Approach 2:
The consumer graph system provides universal data integration capabilities that work across all media platforms simultaneously, allowing a single system to serve multiple functions: integrating data from diverse sources, performing cross-device association, and generating platform-specific optimization strategies
3Device complexity
If current advertising systems are used, then existing infrastructure can be maintained, but the ability to associate devices with precise audiences and predict consumer behavior is insufficient
Solution Approach 1:
The patent implements dynamic device association that adapts to changing consumer behavior patterns by continuously updating the consumer graph with new data, allowing the system to dynamically adjust device-to-audience associations rather than relying on static, pre-defined relationships
Solution Approach 2:
The patent adds a new dimension of analysis by creating a graph-based consumer model that represents consumers as nodes connected to their devices and behaviors, transforming traditional flat advertising data structures into multi-dimensional graph relationships that enable precise audience association and behavior prediction
Data Source
AI summary
A method may include obtaining a data set associated with viewing of digital content. The method may also include matching at least a portion of the data set to at least one consumer in a consumer graph to obtain person matched data. The method may further include extrapolating the person matched data to a total audience. The method may also include obtaining a total estimate of viewership data associated with the viewing of the digital content based on the extrapolated person matched data. The method may further include obtaining a viewership estimate of the digital content based on the total estimate of viewership data and the data set.