Amazon Technologies, Inc.

Hoda Parvin

Guillermo Bravo Beneitez

Rico Polim

Anthony Joseph Battista

Timothy Lee Jacobs

Russell John Allgor

David John Michael

Ozlem Bilginer

Jennifer S Hwang

Sakshi Trivedi

Jason O'brien Hawkes

Kelly Michelle Lohr

Andres Ignacio Ayala Armanet

Chaitanya Sankuratri

Kenil Vora

Katherine Elizabeth Sbordon

This disclosure is directed to systems and techniques for generating actionable metrics data based on sensor data generated from one or more sensors within an environment. For instance, a brick-and-mortar retail environment or other materials handling facility may include one or more sensors, such as overhead cameras, which generate image data as users interact with items in the environment. Machine-learning models and/or computer-vision algorithms may then analyze the resulting image data to identify the interactions between the users and the items. The system may then generate metrics data indicating varying metrics associated with these interactions, which may be used to generate graphical user interfaces (GUI) for presenting the metrics data to vendors, brand owners, and the like.

Generating actionable metrics from sensor data

This disclosure describes, in part, systems for recommending items and item placements within a facility. For instance, the system may receive transaction data and inventory data associated with at least the facility. The system may then use the transaction data and the inventory data to determine utility scores for items at the facility. Additionally, the system may receive data representing dimensions of the items and/or data representing dimensions of available space associated with the facility. The system may then use the utility scores, the dimensions of the items, and/or the dimensions of the available space to determine the amounts of space to provide to the items at the facility. Furthermore, the system can generate data representing an assortment of the items, where the assortment indicates at least the amounts of space, and provide the data to one or more computing devices.

Systems for selecting items and item placements

Features related to systems and methods for network planning based on optimization modeling of equipment and item transmissions. The network planning may include a model to plan for transmission of items over a network to maximize overall efficiencies over alternative transmission modes. The model may produce a network plan that schedules transmissions, determines the number and types of equipment needed to support the transmissions, assigns equipment to specific locations, and optimally routes items throughout the network.

Network planning and optimization

Growing community of inventors

Seattle, WA, United States of America

Hoda Parvin