Parallel Data Pool Processing for Content Selection Speed
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing content delivery systems face challenges in selecting relevant content for users within short timeframes, especially when dealing with large volumes of potential content, leading to inefficiencies in user engagement and interaction.
Innovation Solution
The implementation of parallel data pool processing and intelligent item selection systems that utilize evaluation engines and databases to evaluate multiple content options simultaneously, considering contextual factors like user interactions and bid requests, to determine the most relevant content for presentation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If traditional sequential content selection methods are used, then system complexity is low, but content selection speed and relevance are insufficient for large volumes of content
Solution Approach 1:
The patent segments the content selection system into multiple independent evaluation engines, each responsible for evaluating specific content items from different data pools. This parallel segmentation enables simultaneous content evaluation across multiple threads, dramatically increasing selection speed while maintaining manageable system complexity through modular architecture
Solution Approach 2:
The patent introduces a temporal dimension by implementing time-based prioritization queues that process content requests based on deadlines and urgency. This adds a time-axis dimension to the traditional content selection process, enabling efficient handling of large content volumes by prioritizing time-sensitive selections without overwhelming system complexity
2Reliability
If multiple content options are evaluated simultaneously, then content relevance and user engagement improve, but processing time and computational resources increase
Solution Approach 1:
The patent implements preliminary action by pre-processing and organizing content into prioritized queues before actual selection requests arrive. Content items are pre-evaluated for basic relevance metrics and organized by priority levels, so when selection requests occur, the system can quickly retrieve and finalize selections without performing complete evaluations from scratch, reducing processing time while maintaining relevance
Solution Approach 2:
The patent applies partial action by implementing incremental evaluation where content items are assessed using progressively refined criteria. The system performs initial quick-filtering on large content volumes, then applies more detailed relevance checks only to candidates that pass preliminary thresholds. This staged approach achieves high content relevance without the computational overhead of evaluating all items with full scrutiny
3Adaptability or versatility
If large volumes of content data are processed, then content variety and selection quality improve, but system resource consumption and processing overhead increase
Solution Approach 1:
The patent segments large content data volumes into multiple manageable data pools, each handled by dedicated evaluation engines. This segmentation allows the system to process diverse content types efficiently by routing different content segments to specialized processors, maintaining high content variety while improving overall processing efficiency through parallel operations
Solution Approach 2:
The patent implements universal evaluation engines that can handle multiple content types and formats through a unified processing framework. These multi-functional engines apply consistent evaluation criteria across diverse content while adapting to specific content characteristics, enabling efficient processing of large content volumes with high variety without requiring separate specialized systems for each content type
Data Source
AI summary
Systems, methods, and computer-readable media are disclosed for parallel data pool processing and intelligent item selection. In one embodiment, an example method may include determining a first bid request comprising a first user identifier, determining a first set of product identifiers in a first user interaction history of the first user identifier, determining a second bid request comprising a second user identifier, and determining a second set of product identifiers in a second user interaction history of the second user identifier. Example methods may include determining estimated values for one or more product identifiers in the first set of product identifiers and the second set of product identifiers in parallel, and generating respective first and second responses to the first bid request and the second bid request using the estimated values.