AI Conversion Score Neural Network for Digital Content Targeting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional targeted digital content systems face inaccuracies, inefficiencies, and inflexibility in identifying and distributing digital content to target entities, due to their reliance on historical data and individual-level analysis.
Innovation Solution
The use of an artificial intelligence approach that includes a conversion activity score neural network to predict conversion probability scores and a persona prediction machine learning model to identify key personas for target entities, enabling more accurate and efficient digital content distribution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional systems distribute digital content based on historical performance data, then they can maintain operational simplicity, but they suffer from inaccuracy in identifying target entities and devices
Solution Approach 1:
The patent replaces conventional mechanical analytical approaches with artificial intelligence and machine learning models. Specifically, it uses a conversion activity score neural network to predict conversion probabilities and a persona prediction machine learning model to identify key personas, substituting traditional rule-based content distribution systems with AI-driven predictive analytics to improve accuracy in identifying target entities and devices
Solution Approach 2:
The patent changes the parameters used for content distribution from simple historical performance metrics to complex AI-generated predictions including conversion activity probability scores and persona classifications. By transforming input parameters from basic historical data to sophisticated AI model outputs, the system achieves higher measurement precision in identifying relevant target entities while accounting for updated circumstances
2Productivity
If conventional systems distribute digital content to all identified devices, then they ensure broad coverage, but they waste computing resources on devices that cannot or will not take actions
Solution Approach 1:
The patent applies partial action by using the conversion activity probability score to selectively distribute content only to devices with high predicted conversion probability. Instead of distributing to all identified devices, the system performs partial distribution based on AI-predicted likelihood of conversion, thereby avoiding waste of computing resources on devices unlikely to convert while maintaining high productivity in content distribution
Solution Approach 2:
The patent implements feedback mechanisms where the AI models continuously learn from actual conversion outcomes to refine future content distribution decisions. The system uses feedback from past content distribution results to improve the accuracy of conversion probability predictions and persona identification, enabling progressively more efficient resource allocation and reduced waste of computing resources
3Ease of operation
If conventional systems use multiple user interfaces for content distribution, then they provide comprehensive functionality, but they require excessive client device interactions to navigate
Solution Approach 1:
The patent merges multiple user interface functions into a single integrated interface that displays both the entity conversion activity interface with conversion probability scores and the key personas interface with identified personas. By combining previously separate interfaces for content distribution and persona analysis into one unified interface, the system reduces the number of client device interactions required while maintaining comprehensive functionality
Solution Approach 2:
The patent creates a universal user interface that performs multiple functions simultaneously - displaying conversion activity scores, identifying key personas, and enabling content distribution decisions all in one interface. This multi-functional interface eliminates the need to navigate between separate applications or interfaces, significantly reducing client device interactions and time loss while providing complete content distribution capabilities
4Measurement precision
If conventional systems focus on individual client devices, then they achieve detailed analysis, but they fail to recognize inter-relationships among devices within the same entity
Solution Approach 1:
The patent adds a new dimension to content distribution analysis by incorporating entity-level context alongside individual device analysis. The persona prediction machine learning model identifies key personas within entities, and the system uses this entity-dimensional perspective to understand inter-relationships among devices. This dimensional expansion allows the system to maintain detailed individual device analysis while simultaneously recognizing and utilizing relationships among devices within the same entity for more accurate and adaptable content distribution
Data Source
AI summary
The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and efficiently predicting conversion probability scores and key personas for target entities utilizing an artificial intelligence approach. For example, the disclosed systems utilize a conversion activity score neural network to predict conversion activity probability scores for target entities and utilize a persona prediction machine learning model to predict key personas associated with target entities. In particular, the disclosed systems utilize the conversion activity score neural network to generate a predicted conversion activity probability score for a target entity from input data including client device interactions of digital profiles belonging to the target entity as well as an entity feature vector representing characteristics of the target entity. The disclosed systems also (or alternatively) utilize a persona prediction machine learning model to determine a set of key personas for the target entity from the entity feature vector.