Automated Sponsored Content Generation via Machine Learning Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing online systems lack the technical capabilities to efficiently generate sponsored content pages within short time frames, especially when third-parties are selected through ad auction processes, and manually creating such pages is laborious and time-consuming.
Innovation Solution
An online system that utilizes a machine-learning model to identify candidate sponsors and generate sponsored content pages by incorporating sponsored items into existing content pages, such as recipe pages, within the system, leveraging a model serving system hosting a machine-learning language model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional manual methods are used to create sponsored content pages, then content quality can be maintained, but the process is laborious and time-consuming
Solution Approach 1:
The patent replaces manual mechanical content creation processes with automated machine-learning models. The system uses trained models to automatically generate sponsored content pages by identifying candidate sponsors, selecting appropriate items, and creating content without human intervention, thereby dramatically improving productivity while reducing time loss.
Solution Approach 2:
The system enables self-service automated content generation where the machine-learning models independently perform sponsor identification, item selection, and content creation tasks. The models serve themselves by automatically processing sponsorship opportunities and generating complete sponsored content pages without requiring manual orchestration.
2Productivity
If automated systems are implemented to generate sponsored content pages quickly, then productivity improves, but the system lacks the technical capabilities required for ad auction processes
Solution Approach 1:
The patent changes the parameters of the automated system by implementing machine-learning models with specific capabilities trained for ad auction processes. The models are configured to handle auction timing, sponsor selection, and content generation within the constrained time frames of ad auctions, thereby achieving both high productivity and reliability.
Solution Approach 2:
The system performs preliminary actions by pre-training machine-learning models with extensive sponsorship and auction data before actual ad auctions occur. This preliminary training and preparation enables the models to quickly and reliably generate sponsored content pages during live auction events without requiring complex real-time decision-making infrastructure.
3Manufacturing precision
If more sophisticated machine-learning models are used to identify candidate sponsors and generate content, then content quality and relevance improve, but system complexity increases
Solution Approach 1:
The patent segments the complex content generation task into distinct components handled by specialized machine-learning models: one model identifies candidate sponsors from sponsorship opportunities, another model selects appropriate items, and additional models generate the actual content. This segmentation allows each model to be optimized for its specific function, improving overall content quality while managing system complexity through modular architecture.
Data Source
AI summary
An online system presents a sponsored content page to a user in conjunction with a model serving system. The online system accesses a content page for a food item and identifies one or more sponsorship opportunities at the content page. The online system identifies one or more candidate sponsors for each sponsorship opportunity. The online system selects a bidding sponsor for the sponsorship opportunity from the one or more candidate sponsors and a candidate item associated with the bidding sponsor as a sponsored item. The online system provides a content page, a description of the sponsored item, and a request to generate a sponsored content page for the sponsorship opportunity to a model serving system. The online system receives a sponsored content page generated by a machine-learning language model at the model serving system and presents the sponsored content page to a user.