Amazon Technologies, Inc.

Min Chong

Leo Parker Dirac

Sean Michael Scott

Blair Livingstone Hotchkies

Anthony T Chor

Paul Christopher Cerda

Bradley Scott Bowman

Kevin Andrew Granade

Udip Pant

Adam Brent Johnson

Llewellyn James Mason

John Riley Lynch

Brian Chang

Francisco Jose Peredo Noguez

Aman Agarwal

Systems and methods for managing content delivery functionalities based on machine learning models are provided. In one aspect, content requests are routed in accordance with clusters of historical content requests to optimize cache performance. In another aspect, content delivery strategies for responding to content requests are determined based on a model trained on data related to historical content requests. The model may also be used to determine above-the-fold configurations for rendering responses to content requests. In some embodiments, portions of the model can be executed on client computing devices.

Machine learning based content delivery

An interactive user interface is disclosed that enables users to efficiently access and/or submit component-specific reviews of components of a product. The user interface displays an image of the product, and displays region identifiers that identify image regions corresponding to product components that are separately reviewable. When a user selects a particular region, the user interface may display component-specific reviews of the corresponding component, and/or may display an option to submit a component-specific review of the component. The user interface may be included in an interactive catalog page, such as a web page.

System with interactive user interface for efficiently accessing component-level reviews

Methods, devices and program products are provided which comprise the under control of one or more computer systems configured with specific executable instructions. The methods, devices and program products provide an image of an item for display, and the item is comprised of a plurality of components. The methods, devices and program products receive a selection of a component of interest from the plurality of components of the item, and obtain a component-level rating associated with the component of interest.

Component-level rating system and method

Growing community of inventors

Kirkland, WA, United States of America

Min Chong