Amazon Technologies, Inc.

Adam James Finkelstein

David Michael Hurley

Siqi Zhao

David Akira Gingrich

Stephen Brent Ivie

Aaron James Dykstra

Ashutosh Vishwas Kulkarni

Saurabh Nangia

Scott James McKee

Siu Nam Wong

Adam Landry Bordelon

Anthony Alexander Santos

Markus Wai-Keen Kwok

Ho Nam Ho

Adam Edward Shirey

Phivos Costas Avistides

Social network postings, including text, images or other media, may provide valuable information regarding a user of the social network with which the postings may be associated. With the authorization of the user, and upon authentication by the social network, an online marketplace may access the social network postings and extract data therefrom, and market one or more recommended items to the user based on the extracted data, which may include color pallets or texture pallets derived from photographs included in the postings.

Social media data matching

A service may create image-based reviews, which include minimal or no text, to assist customers in researching products. The reviews may include images sorted or grouped (e.g., by sentiment, by product review rating, by age of item, by number of uses, etc.). Images of items may be obtained by the service from user reviews and/or other sources. The images may be associated with text, such as at least some text from associated reviews, commentary, and/or other metadata. The images may be analyzed by a classifier to identify features in the visual image, such as a location of a particular item. The images may be categorized for use in one or more user interfaces that provide image-based item reviews. In some embodiments, the images may be arranged based on a number of uses of the item in the image or by an item age of the item in the image.

Image-based item reviews

A digital media service distributes digital media content to a plurality of devices in a graphical processing unit based distributed cluster and transmits executable instructions to these devices to initiate a collaborative filtering algorithm. Accordingly, the graphical processing unit in each of the devices, configured to utilize the collaborative filtering algorithm, may generate one or more co-occurrence vectors comprising similarities among a user's interactions with the digital media content and other users' interactions with the digital media content. These co-occurrence vectors are transmitted to the digital media service, which may create a matrix based at least in part on these vectors to determine personalized digital media content that is to be distributed to each of the devices in the distributed cluster. Accordingly, the personalized digital media content is distributed to each device in the distributed cluster.

Distributed processing for content personalization

A recommendation system uses artificial intelligence to identify, based on negative sentiment cues from users, item attributes, such as keywords, that users may find offensive or undesirable. The negative sentiment cues may be explicit (e.g., a user selects an option not to view a particular recommendation again), implicit (e.g., a user does not interact with recommendations relating to an attribute), or both. The system may use a computer model generated based on these identified attributes to filter or modify recommendations to a user or group of users. For instance, if a particular keyword is identified as highly offensive to a group of users, items associated with the keyword may be filtered from item recommendations presented to the group of users. If an attribute is identified as moderately offensive to a user, items associated with the attribute may be down-weighted in item recommendations presented to the user.

Artificial intelligence based identification of item attributes associated with negative user sentiment

Artificial intelligence based identification of negative user sentiment in event data

Recommendations of items may be provided to a customer who purchases items from an online marketplace on behalf of a user account based on the interactions of the customer with the marketplace or with one or more external resources, such as a social network account affiliated with the customer. For example, systems and methods may utilize such interactions to determine which of the purchases of items on behalf of the user account are affiliated with the customer, and which may be affiliated with one or more other individuals. Similarly, the systems and methods may also identify recommendations for customers who have purchased items for delivery to a destination based on other items that have been delivered to the destination, and may further determine when a customer has purchased an item for a recipient who has already received the item from another customer.

Providing product recommendations based on user interactions

A system that identifies attributes of an item depicted in an image using artificial intelligence is provided. For example, the system may use one or more deep belief networks (DBNs) or convolution neural networks (CNNs) trained to analyze images and identify attributes in items depicted in the images. A first artificial intelligence module may analyze an image to determine a type of item depicted in the image. The system may then select a second artificial intelligence module that is associated with the type of item and use the second artificial intelligence module to identify attributes in the item depicted in the image. Identified attributes, if associated with a confidence level over a threshold value, may be provided to a user. The user may provide feedback on the accuracy of the identified attributes, which can be used to further train the first and/or second artificial intelligence modules.

Identification of item attributes using artificial intelligence

Growing community of inventors

Seattle, WA, United States of America

Adam James Finkelstein