Amazon Technologies, Inc.

Other

Ladan Mahabadi

Malcolm Featonby

John Merrill Phillips

Leslie Johann Lamprecht

Umesh Chandani

Letian Feng

Roberto Pentz De Faria

Hou Liu

Alexander Illichmann

Sudhir Hassan Manikya Raju

Michiel David De Pooter

Francesco Furno

Seema Yadav

Tong Ge

Stebin Kodiamkunnel Sevichan

A user provides a question to be answered from detailed, dense or otherwise complex documents to a processing system that converts the question to a structured query language query and generates an embedding from the question, augmented by temporal data, synopses, themes, or other relevant information or data. The embedding is compared to embeddings generated from documents of a knowledge base to identify documents that are relevant to the question, and to rank such documents for their relevance. Highly ranking documents are combined with the query and provided to a language model that returns an answer to the question. A source for the answer is identified in at least one of the documents. The answer and the identified documents are presented to the user.

Verification and citation for language model outputs

Techniques for an optimization service of a service provider network to help optimize the selection, configuration, and utilization, of virtual machine (VM) instance types to support workloads on behalf of users. The optimization service may implement the techniques described herein at various stages in a life cycle of a workload to help optimize the performance of the workload, and reduce underutilization of computing resources. For example, the optimization service may perform techniques to help new users select an optimized VM instance type on which to initially launch their workload. Further, the optimization service may monitor a workload for the life of the workload, and determine new VM instance types, and/or configuration modifications, that optimize the performance of the workload. The optimization service may provide recommendations to users that help improve performance of their workloads, and that also increase the aggregate utilization of computing resources of the service provider network.

Compute platform recommendations for new workloads in a distributed computing environment

Compute platform optimization over the life of a workload in a distributed computing environment

Determining configuration parameters to provide recommendations for optimizing workloads

Techniques for an optimization service of a service provider network to provide users with machine-generated narratives that include human-intelligible, credible, and transparent recommendations and rationales for recommended VM instance types. The optimization service may gather various information or data about the workload, such as utilization characteristics of the underlying computing resources, and decompose the workloads through a number of dimensions that can be used to describe the workload. Further, the optimization service may analyze the utilization characteristics and/or other data to determine more optimized VM instance types for the workloads that are to be recommended to the users, and also rationales that describes why each recommendation is an appropriate fit for the workload being assessed. Using this information, the optimization service may generate narratives that include a description of the workload behaviors and utilization patterns, a set of recommendations, and supporting narrative or rationales for each of the recommendations.

Generating narratives for optimized compute platforms

Compute platform optimization across heterogeneous hardware in a distributed computing environment

Optimizing hardware platform utilization for heterogeneous workloads in a distributed computing environment

Growing community of inventors

Seattle, WA, United States of America

Ladan Mahabadi