Amazon Technologies, Inc.

Ca, Inc.

Ashish Singh

Vikram Sathyanarayana Anbazhagan

Vasanth Philomin

Swaminathan Sivasubramanian

Stefano Stefani

Andrew Olcott

Walter Manching Tseng

Jeffrey Craig Kunins

Seth Gershom Goldstein

Robert Wayne Roth

Atul Deo

Wainwright Gregory Siady Yu

Otis Yeager Chandler

Anuroop Arora

Jessie Young

Brian David Rosenblat

Deepikaa Suresh

Eric Michael Franklin

Vladimir Zhukov

Pramod Gurunath

Manigandan Natarajan

Sai Eswar Garapati

Varun Sembium Varadarajan

Eric Chen

Pu Paul Zhao

Shanmugarasa Muhunthan

Arjun Subramanian

Manish Jha

Pradeep Kumar Das

Vijit Gupta

Ruoyu Huang

Jay Prashant Subhash

Manikanta Aditya Pasalapudi

Harsh Yadav

Varun Jakhoria

Priyanka Shirish Kale

Colin Thomas Davidson

Katrin Kirchoff

Yasser El-Haggan

Rajkumar Gulabani

Praveen Kumar Akarapu

Robert Hale Christensen

Vijay Kishore Kalakotla

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

A system for generating heat map data for content. The system may include a user device, which may capture user input to begin presentation of the content and stop presentation of the content. The user device may also capture information associated with a time interval associated with the user input. The time interval may include a start time and an end time. The user device may send the user input and the information to a server. The server may collect user inputs and information from multiple user devices which are used to generate user interface data. The user interface data may be configured to cause a depiction of a user interface element. The user interface element may include one or more indicators that identify an interest portion associated with the time interval within the content. The indicators enable a user to locate or know interesting portions within the content.

System and method for generating user interface data to provide indicators associated with content

A metadata item may be generated that includes metadata content corresponding to a selected portion of digital content stored on a first device, the metadata item may be associated with a first user profile, and the metadata item may be distributed to a second user device storing the digital content such that the metadata item can be accessed via a second user profile and rendered on the second user device in association with the digital content. In this manner, metadata content corresponding to digital content may be shared across user profiles that access the digital content. In addition, a collaborative content item may be generated that includes collaborative content associated with a word or phrase in digital content and that is editable by multiple user profiles.

Generation and distribution of collaborative content associated with digital content

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

Systems, methods, and computer-readable media are disclosed for detecting and rendering endnotes in digital content. A user selection of a link rendered at a first location in digital content may be detected and various filtering criteria may be evaluated to determine whether the link references a second location in the digital content that is associated with endnote content. If the link is determined to reference endnote content, the endnote content may be extracted and rendered in association with a portion of the digital content corresponding to the first location.

Detection and rendering of endnotes in digital content

A method includes storing a plurality of workloads in a first disk resource associated with a high end disk classification. The method further includes determining a corresponding activity level for each of the plurality of workloads. The method also includes classifying each of the plurality of workloads into a first set indicative of high-priority workloads and a second set indicative of low-priority workloads based on whether the corresponding activity level is greater than a threshold activity level. The method further includes determining whether a second disk resource associated with a low end disk classification can accommodate storage of a first particular workload in the second set based on an available storage capacity of the second disk resource. The method additionally includes migrating the first particular workload from the first disk resource to the second disk resource.

Prioritizing and distributing workloads between storage resource classes

Distribution of user-generated annotations associated with digital content

A method includes instantiating a virtual resource and, in response to instantiating the virtual resource, generating a snapshot image comprising a base configuration of the virtual resource. The method also includes receiving a request to de-provision the virtual resource and, in response to receiving the request to de-provision the virtual resource, determining, using a processor, whether the base configuration of the virtual resource is in a set of highly utilized virtual resource configurations based on virtual resource utilization data. The method further includes, in response to determining that the base configuration of the virtual resource is in the set of highly utilized virtual resource configurations: reverting the virtual resource to its base configuration using the snapshot image and allocating the virtual resource to a resource pool.

Reverting a virtual resource to its base configuration using the snapshot image based on frequency the virtual resource is requested

Growing community of inventors

Seattle, WA, United States of America

Ashish Singh