Suppression Filter Parallel Processing Reduces Latency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing web page content recommendation systems face challenges in managing latency, leading to prolonged responsiveness and an unacceptable user experience due to the need for efficient determination and loading of content, particularly when suppressing recommendations based on user interactions.
Innovation Solution
The implementation of suppression filters stored in category-level data structures, allowing for parallel processing of content recommendation and suppression filter determination, reduces the number of look-ups and latency by associating account data with item categories, thereby optimizing the presentation of content within a target time frame.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If suppression filters are applied to determine content recommendations, then content relevance is improved, but processing latency increases
Solution Approach 1:
The patent segments the suppression filter determination process into distinct components: identifying suppressed item categories based on user interactions, separately determining content recommendations, and then filtering recommendations against suppressed categories. This segmentation allows parallel processing of suppression filter identification and content recommendation generation, reducing overall processing latency while maintaining content relevance.
Solution Approach 2:
The patent implements preliminary action by pre-identifying suppressed item categories based on user interaction history before the content recommendation process begins. The suppression filters are established in advance using stored user interaction data, allowing the recommendation engine to work with pre-filtered categories rather than applying filters during the recommendation generation process, thereby reducing processing latency.
2Measurement precision
If detailed user interaction history is analyzed for suppression filters, then content relevance is improved, but device complexity increases
Solution Approach 1:
The patent extracts only the essential information needed for suppression filter determination from detailed user interaction history. Instead of analyzing complete interaction histories, the system extracts suppressed item categories and associated suppression times, storing them in simplified data structures. This extraction approach maintains content relevance while reducing device complexity by eliminating unnecessary data storage and processing requirements.
Solution Approach 2:
The patent applies local quality by implementing suppression filters at the item category level rather than requiring detailed analysis of individual item interactions. The suppression filter data structures store category-level suppression information, allowing the system to make recommendation decisions based on category suppressions rather than analyzing each individual user interaction in detail, thereby reducing data structure complexity while maintaining effective content filtering.
Data Source
AI summary
Techniques for using suppression filters for presenting content of a network documents are described. In an example, a computer system receives, from a device associated with an account identifier, a request for an online network document. The computer system determines that a first category identifier of a first item category is associated with a suppression filter. The computer system determines that the account identifier is associated with an online item interaction having an interaction time associated with an item that belongs to the first item category. The computer system determines, based on a comparison of the interaction time and the suppression time, that a presentation of the first content in the online network document is prohibited. The computer system sends, to the device in response to the request, network document data that indicates second content about a third item that belongs to a second item category.