Amazon Technologies, Inc.

Shaw Parsing LLC

Brian Cameros

Peter D Cohen

Rahul H Bhagat

Isaac E Nichols

Srikanth Thirumalai

Scott Allen Mongrain

Logan Luyet Dillard

Grant Michael Emery

Adam Callahan Sanders

Benjamin Thomas Cohen

Yongwen Liang

Eli Glen Rosofsky

Wade Albright

Michael David Quinn

The present technology may identify item category affinities by identifying a plurality of classifications of an item. An accuracy of the plurality of classifications relative to one another for the item may be identified. A category affinity of the item may be determined based on the accuracy of the plurality of classifications relative to one another.

Video classification

The content provider provides content to the first data center, which then provides the content to the client. The client determines that a failure between content provider and the first data center may have occurred. When the client determines that a failure may have occurred, the client may connect to a second data center to receive content from the content provider through the second data center. Accordingly, the failure is detected and additionally, automatic failure recovery may be provided at the client.

Techniques for upstream failure detection and failure recovery

The use of graph-based semantic analysis with respect to items and tags may enable the discovery of the characteristics of items. A tag collection component may initially obtain a corresponding set of tags for each item of multiple items. A graph generation component may then generate a graph that includes a corresponding item node for each item and a corresponding tag node for each tag cluster of tags. Each item node in the graph may be connected to each of one or more tag nodes by a respective edge. Subsequently, following assignment of a label to each tag node, a graph evaluation component may execute a random walk algorithm on the graph. The execution of the random walk algorithm may provide a corresponding ranked list of tags for each item or a corresponding set of correlated tags for each tag.

Graph-based semantic analysis of items

Techniques are described for facilitating interactions between task requesters who have tasks available to be performed and task performer users who are available to perform tasks, such as interactions that enable improvement of unsatisfactory task performance results from human task performer users. In some situations, after a task performer user has generated initial results from performance of a task supplied by a task requester, the task requester indicates that the initial results are only partially satisfactory (e.g., only partially satisfy one or more criteria for the task performance results), and may result in only a partial payment rather than a full payment amount associated with fully satisfactory performance of the task. The task requester may also supply information to provide one or more opportunities to the task performer user to supply additional improved supplemental results (e.g., so as to receive the full payment amount).

Facilitating improvement of results of human performance of tasks

Growing community of inventors

Seattle, WA, United States of America

Brian Cameros