Amazon Technologies, Inc.

Vikram Sathyanarayana Anbazhagan

Swaminathan Sivasubramanian

Stefano Stefani

Vladimir Zhukov

Ashish Singh

Vasanth Philomin

Atul Deo

Anuroop Arora

Jessie Young

Deepikaa Suresh

Rama Krishna Sandeep Pokkunuri

Pramod Gurunath

Varun Sembium Varadarajan

Yue Yang

Pu Paul Zhao

Patrick Ludvig Bajari

Jeffrey Paul Helbling

Jeffrey L Belle

Kelly Paulson

Vijit Gupta

Constantin Daniel Marcu

Ganapathy S Srivathsan

Praveen Kumar Akarapu

Ana Maria Mocanu

Harsh Yadav

Priyanka Shirish Kale

Ruoyu Huang

Colin Thomas Davidson

Rajkumar Gulabani

Yasser El-Haggan

Yang Li

Katrin Kirchoff

Kai Gao

Xu Zhao

Generative machine learning models may be used to generate a transcreated version of input data. A transcreation request to generate a translated version of the input data may be received. One or more instructions for the input data may be determined based at least in part on an aggregated transcreation style identified for the request. A generative machine learning model may be used to generate the translated version of text in a source natural language that is associated with the input data according to the one or more instructions. The created version of the input data may be provided.

Dynamic generation of instructions for machine learning transcreation tasks

A determination is made as to whether a value of a first parameter of a first application is to be obtained using a natural language interaction. Based on received input, a first service of a plurality of services is identified. The first service is to be used to perform a first task associated with the first parameter. Portions of the first application to determine the value of the first parameter and to invoke the first service are generated.

Back-end task fulfillment for dialog-driven applications

This disclosure describes a container management tool of a container management service of a service provider network that operates a first container in a network mode associated with a software generated namespace generated by the container management tool. The container management tool determines a location of the software generated namespace and adds a link to a desired, e.g., existing application network namespace to the software generated namespace. The container management tool, using an application namespace creation script, generates a name for the desired application network namespace. The service provider network executes one or more first applications in the first container, wherein executing the one or more first applications in the first container comprises the first container accessing the software generated namespace and following the link to the desired application network namespace.

Operating containers in existing network namespaces in a service provider network

Systems and methods to implement customer contact service with real-time supervisor assistance. A supervisor may oversee multiple agents in a customer contact service. A service of a computing resource service provider may monitor a plurality of audio connections at a service of a computing resource service provider, generate transcripts for the plurality of audio data, analyze the transcripts using a set of natural language processing (NLP) techniques to generate metadata, tag the transcripts with categories based at least in prat on the metadata, generate information for at least a portion of the plurality of connections based on the transcripts, metadata, and categories, and provide the information to a supervisor of the agents.

Customer contact service with real-time supervisor assistance

Systems and methods to analyze contacts data. Contacts data may be encoded as text (e.g., chat logs), audio (e.g., audio recordings), and various other modalities. A computing resource service provider may implement a service to obtain audio data from a client, transcribe the audio data, thereby generating text, execute one or more natural language processing techniques to generate metadata associated with the text, processing at least the metadata to generate an output, determine whether the output matches one or more categories, and provide the output to the client. Techniques described herein may be performed as an asynchronous workflow.

Systems and methods to analyze customer contacts

Techniques for streaming real-time automated speech recognition (ASR) are described. A user can stream audio data to a frontend service of the ASR service. The frontend service can establish a bi-directional connection to an audio decoder host to perform ASR on the data stream. The audio decoder host may include a streaming ASR engine which can analyze chunks of the audio data stream using an acoustic model to divide the audio data into words, and a language model to identify sentences made of the words spoken in the audio file. The acoustic model can be trained using short audio sentence data (e.g., on the order of 30 seconds to a few minutes), enabling the transcription service to accurately transcribe short chunks of audio data. The results are then punctuated and normalized. The resulting transcript is then streamed back to the user over the bi-directional connection.

Streaming real-time automatic speech recognition service

Techniques for automated speech recognition (ASR) are described. A user can upload an audio file to a storage location. The user then provides the ASR service with a reference to the audio file. An ASR engine analyzes the audio file, using an acoustic model to divide the audio data into words, and a language model to identify the words spoken in the audio file. The acoustic model can be trained using audio sentence data, enabling the transcription service to accurately transcribe lengthy audio data. The results are punctuated and normalized, and the resulting transcript is returned to the user.

Fully managed and continuously trained automatic speech recognition service

Methods, systems, and computer-readable media for exporting dialog-driven applications to digital communication platforms are disclosed. A launch condition is received from a user. The launch condition is caused to be registered with one or more digital communication platforms. Detection of the launch condition is to cause a natural language input to be routed from at least one of the digital communication platforms to an application management service.

Exporting dialog-driven applications to digital communication platforms

A natural language understanding model is trained using respective natural language example inputs corresponding to a plurality of applications. A determination is made as to whether a value of a first parameter of a first application is to be obtained using a natural language interaction. Using the natural language understanding model, at least a portion of the first application is generated.

Service for developing dialog-driven applications

Based on historical data describing product sales or other types of transactions, indicator scores may be calculated for users who have purchased, reviewed, or otherwise consumed products, the indicator scores based on subsequent diffusion of the products. Measured, current activities of the scored users with regard to another product may then be employed to develop a diffusion model that predicts the future sales of the other product over time. The diffusion model may be employed to determine product pricing, marketing, distribution, or acquisition.

Diffusion prediction based on indicator scoring

Growing community of inventors

Seattle, WA, United States of America

Vikram Sathyanarayana Anbazhagan