Amazon Technologies, Inc.

Vmware, Inc.

Amazon Technology, Inc.

Intec Billing, Inc.

Ashish Kumar Agrawal

Robert Frederick

Amit Bhosle

Jeffrey Barr

Gunavardhan Kakulapati

James R McCann, Iii

Peter Sirota

Don Johnson

Tushar Jain

Dhanvi Harsha Kapila

Sudharsan Thumatti Sathiamoorthy

Gaurav D Ghare

Amit Jain

Rohit Pradeep Shetty

Hilliard Bruce Siegel

Shree Harsha Shedigumme

Sharun Varghese Samuel

Ezra Cooper

Hendi Chandi

Vineesh Sinha

Arindam Mandal

Scott Gerard Carmack

Sachin Purushottam Joglekar

Raefer Christopher Gabriel

Shilpi Gupta

Mehul Jain

Shree Harsha S

Mohammed Sujayath Ali

Sravana Kumar Karnati

James Vernon Reagan

Dilip Kumar Sivasankar

Mark V Stabingas

Shaleen Mittal

Yue Liu

Ammar Chinoy

Haoyu Wang

Ian Ragsdale

Saurabh Agrawal

Siddhartha Reddy Jonnalagadda

Prakash Krishnan

Prashant Shelke

Kemal Oral Cansizlar

Ruben Nieves

Suranjit Adhikari

Shishir Sridhar Bharathi

Savas Parastatidis

Yogesh Vhora

Nikhil Jere

Anushree Venkatesh

Makarand Gawade

Santhosh Chandrashekarappa

Avinash Bhattarmakki

James J Logan

Albert J Morello

Tong Wang

Abhay Kumar Jha

Michael Donikian

David Chi-Wai Tang

Swaroop Rajendra

Meghana Holemadlu Murthy

Meenakshi Ambaram Ragavan

Guarav D Ghare

Shucheng Zhu

Han Wang

Yun Lei

Arjit Biswas

This disclosure proposes systems and methods for entity resolution using speech recognition data. The system can receive audio data representing an utterance and perform automatic speech recognition (ASR) processing on the audio data to generate at least a first ASR data and a second ASR data. The system can perform natural language understanding (NLU) processing on the first ASR data to determine intent data and an indication of an entity. The system can determine a first portion of the first ASR data that corresponds to the indication of the entity. The system can determine a second portion of the second ASR data that corresponds to the indication of the entity without performing NLU on the second ASR data. The system can perform entity resolution (ER) on the second portion to identify a first entity.

Entity resolution using speech recognition data

Techniques for storing and using multi-session context are described. A system may store context data corresponding to a first interaction, where the context data may include action data, entity data and a profile identifier for a user. Later the stored context data may be retrieved during a second interaction corresponding to the entity of the second interaction. The second interaction may take place at a system different than the first interaction. The system may generate a response during the second interaction using the stored context data of the prior interaction.

Multi-session context

Techniques for conversation recovery in a dialog management system are described. A system may determine, using dialog models, that a predicted action to be performed by a skill component is likely to result in an undesired response or that the skill component is unable to respond to a user input of a dialog session. Rather than informing the user that the skill component is unable to respond, the system may send data to the skill component to enable the skill component to determine a correct action responsive to the user input. The data may include an indication of the predicted action and/or entity data corresponding to the user input. The system may receive, from the skill component, response data corresponding to the user input, and may use the response data to update a dialog context for the dialog session and an inference engine of the dialog management system.

Dialog management system

Disclosed are various approaches for workflow service email integration. In some examples, an email application executed on a client device receives an email message that includes a workflow micro application. The workflow micro application has a workflow information component, and evaluation component, and a workflow actions component. The evaluation component identifies a presence or an absence of a management software development kit (SDK) on the client device. The email application renders a user interface that shows or hides a workflow actions interface area based on the presence or absence of the management SDK.

Workflow service email integration

Examples described herein include systems and methods for providing push notifications to a third-party application executing on a client device. An example can include encrypting user credentials, generating a callback Uniform Resource Locator ('URL') with at least a portion of the encrypted credentials embedded into the URL, and requesting notifications from an email service to be provided at the callback URL. Upon receiving a notification at the callback URL, a system component can decrypt the credentials within the URL using a private key and log into the email account using those decrypted credentials. The system component can then generate a push notification based on any changes found in the email account and cause the notification to be delivered to the third-party application on the client device.

Email notification system

A rollback can be performed after completing an upgrade to components of a virtualized computing environment. When the upgrade is performed, an upgrade bundle having rollback scripts is provided to edges, hosts, and managers in the virtualized computing environment that are to be upgraded. When a rollback is to be performed, the rollback scripts are executed, and the components are rolled back in a reverse order relative to their upgrade order. Data and configuration checking are performed to validate the results of the rollback.

Automated rollback in virtualized computing environments

Disclosed are various embodiments for integrating client applications with hosted applications. For example, an email can be received from an email client. It can then be determined whether the email is associated with a hosted application. In response to a determination that the email is associated with the hosted application, a request can be made to a connector for a calendar object. The calendar object is then received and returned to the email client.

Integration of client applications with hosted applications

A shared 'universal' virtual shopping cart ('the cart') may be provided by a host to enable information sharing between multiple disparate electronic marketplaces provided by various merchants. The host may obtain user information via the cart to improve interactions with a user. The host may recommend an item to the user that is offered at a lower price and related to an item retained in the user's cart. The host may also recommend items based on a user's purchase history, such as complementary items (e.g., up-sell items) and items other users may recommend. In some aspects, the host may compile best selling lists based on data from multiple electronic marketplaces. The host may also perform user specific operations such as indicate an item in a cart is a duplicate of a previous purchase and monitor a price and/or available quantities of an item in the cart.

Electronic marketplace recommendations

Techniques for processing complex natural language inputs are described. A complex natural language input may be semantically tagged and parsed to identify individual clauses in the complex natural language input. An execution graph may be generated to represent the clauses and their dependencies. Nodes of the execution graph may be processed using NLU processing and/or a knowledge graph or other information storage and retrieval techniques, and results of such processing may be used to update clause variables with specific entities in the execution graph.

Complex natural language processing

A machine learning (ML) model is created via training or re-training one or more ML algorithms using past release(s) data (e.g., data comprising of requirements and corresponding test cases). The ML model comprises various clusters and these clusters are dynamically created every time when the ML model is trained (or retrained). One or more requirements exist in each cluster, and each requirement has one or more test cases associated with it. New requirements are mapped to a particular cluster and then test cases are compared against a universe of other test cases to determine whether to add a particular test case to a list of test cases that test the new requirement.

Systems and methods to optimize testing using machine learning

Disclosed are various approaches for workflow service email integration. In some examples, a request is transmitted to a workflow service. The request includes workflow content associated with an email message being composed. A workflow micro application associated with the workflow content is received form the workflow service. The workflow micro application is generated using network service data retrieved from a network service. The workflow micro application includes: an information component that renders the network service data for display within the email message. The workflow micro application also includes an evaluation component that evaluates a management status of a client device.

Disclosed are various approaches for connecting third-party services for user interaction. A user can select content on a user interface associated with a first third-party service. The content can be associated with a second third-party service. A client application can transmit the content to an integrated service over a network in a request to obtain additional information from the second third-party service. The integrated service can transmit the additional information to the client application. The user interface can be modified to include a user interface element containing the information associated with the second third-party service.

Integrating related third-party services using dynamically generated user interfaces

A computer process enables a target window associated with a first domain to receive a message from a child window associated with a second domain. The message is passed using an iframe that is created within the target window. The process may, for example, be used to relay information entered by a user into the child window to the target window.

Cross-domain communications between browser windows

Disclosed are various approaches for connecting third-party services for user interaction. An integration service can receive from a client device a content query including a selection of content by a user interacting with a user interface on the client device. The integration service can compare the content query with predefined connector data to identify a connector associated with the content query. The integration service can send the content query and an authentication token of the user to the connector to access information from a third-party service. In response to receiving the information from the third-party service, the integration service can provide the information to the client device.

Integrating related third-party services for user interaction

A method and system for conducting a chat session with multiple chat members. The chat system receives chat comments from the chat members. The chat system attempts to identify a topic or subject of the chat comment. The chat system may then retrieve product or product category advertisements relevant to the identified topic. The chat system then effects the display of the chat comment along with the retrieved advertisements to each chat member. The chat system thus dynamically recognizes the topic of chat comments and displays relevant additional information along with the chat comments.

Method and system for conducting a chat

Growing community of inventors

Mountain View, CA, United States of America

Ashish Kumar Agrawal