US Patent Application 18318513. Two-Layer Bandit Optimization for Recommendations simplified abstract
Contents
Two-Layer Bandit Optimization for Recommendations
Organization Name
Inventor(s)
Siyong Ma of Brookline MA (US)
Debankur Naskar of San Jose CA (US)
Chandrasekar Venkataraman of Los Altos CA (US)
Sofia M. Nikolakaki of San Jose CA (US)
Two-Layer Bandit Optimization for Recommendations - A simplified explanation of the abstract
This abstract first appeared for US patent application 18318513 titled 'Two-Layer Bandit Optimization for Recommendations
Simplified Explanation
- The patent application describes a search interface that includes a search query input component and a suggested results section. - The suggested results section displays potential search results based on the likelihood of selection for each item. - The suggested results are also influenced by the user's search session history, taking into account their previous selections from similar suggested result regions. - The aim is to provide more relevant and personalized search suggestions to improve the user experience.
Original Abstract Submitted
A search interface is presented with a search query input component and a suggested results section. The suggested results section includes potential search results selected based on a likelihood of selection of each of the selectable items and a search session history corresponding to a historic selection of each of the selectable items from prior suggested result regions.
