Amazon Technologies, Inc.

Yu-Hsiang Cheng

Collin Charles Davis

Milo Oostergo

Jonathan Alan Leblang

Aakarsh Nair

Kevin Crews

Gary Zhong

Jingyu Ji

Ruoyu Fei

Richard Christopher Green

Aapo Juhani Laitinen

Cassity Barrows Queen

Krishnamurthy Ganesan

Dick Clarence Hardt

Nicolas Cyril Guillaume

Aaron Gowatch

Surabhi Raje

Karthik Bellur

Siddhartha Shankara Rao

Ajaykumar Selvaraj

Robert Dale Francis

Da Chen

Christopher Chad Lake

Alan Lau

Hanyu Liu

Haifeng Xu

This disclosure describes a feedback service that collects feedback for skills, or capabilities, of a virtual assistant that interacts with users, and associates the feedback with the appropriate skills. Virtual assistants interact with users via voice-enabled devices that are backed by voice-processing systems that support various skills of the virtual assistants. Due to large numbers of skills, users are unable to determine which skill is invoked during interactions with virtual assistants, and are thus unable to provide feedback for the skill. The techniques described herein include continuing a speech dialogue with a user after completion of an interaction, and requesting feedback regarding the interaction. Additionally, the techniques may include collecting contextual data for the interaction (e.g., dropped packets, latency caused by jitter, etc.). The feedback service can associate the feedback and contextual data with the particular skill used in the interaction to improve the functioning of the virtual assistant.

Centralized feedback service for performance of virtual assistant

Systems and methods are disclosed related to determining and providing contextual information associated with a meeting based in part by parsing text from a meeting invitation or calendar entry. A voice-capturing device may receive audio data before or during a meeting that includes an invocation phrase used to invoke a voice-based functionality. A response may be generated by the voice-capturing device or an associated service provider system based on the contextual information determined from the parsed meeting invitation and/or related sources.

Contextual parsing of meeting information

Methods, systems, and computer-readable media for batch registration and configuration of devices are disclosed. A plurality of devices are detected over one or more networks. Data indicative of the plurality of devices is provided through a user interface. Through the user interface, user input is received that indicates a selected plurality of the devices. The selected plurality of the devices are registered with a service provider environment. The selected plurality of the devices are authenticated using device-specific credentials and registered for device-specific accounts with the service provider environment. A configuration profile is deployed to the selected plurality of the devices.

Batch registration and configuration of devices

Techniques for selecting a meeting to join in response to a voice command from a user are described herein. A user may utter a voice command to 'join my meeting' and, in response, the techniques may access a calendar associated with the user to identify the call-in information used to join the meeting. If the calendar indicates that the user is listed as an invitee for multiple meetings at the current time, then the techniques may analyze an array of criteria to determine which meeting the user most likely would like to join.

Selecting meetings based on input requests

Methods, systems, and computer-readable media for location-based functionality for voice-capturing devices are disclosed. An association is determined between a location value for a location parameter and one or more functionalities. The association is stored by a device management component of a service provider environment. An assignment of the location value to a device account is stored by the device management component. The device account corresponds to a voice-capturing device coupled to the service provider environment over one or more networks. Based at least in part on the assignment of the location value to the device account, the one or more functionalities are enabled for use by the voice-capturing device.

Location-based functionality for voice-capturing devices

Systems and methods are disclosed related to determining device settings for a meeting based in part by parsing text from a meeting invitation or calendar entry, and controlling one or more remotely controllable devices during the meeting according to the determined settings. Based on contextual information determined from a parsed meeting invitation and/or related sources, controllable devices such as remote-controllable window shades, lighting equipment, camera equipment, display screens and/or other in-room equipment may be automatically assigned to determined settings before or during an in-person meeting, conference call or videoconference.

Device control based on parsed meeting information

A system is provided that determines a location of a user based on various criteria. The system may detect the location of a user based on the location of the user's device, as determined using a beacon signal, and an expected location of the user's device, as determined using schedule information. The system may process data representing the user's device location and expected location using a model to determine a confidence that a user is at a particular location. Based on the determined location, the system may perform various actions.

Multi-factor location-based authentication

A system is provided that determines a location of a user based on various criteria. The system may detect the location of a user based on the location of the user's voice and the location of the user's device, as determined using a beacon signal. The system may process data representing the user's voice and device locations using a model to determine a confidence that a user is at a particular location. Based on the determined location, the system may perform various actions.

Multi-factor location-based and voice-based user location authentication

Described are techniques for establishing secure communication channels between user devices and service providing devices. Correspondence between a request received from a user device and security data may be used to determine that the user device has provided a valid access credential. The access credential may be replaced with a subsequent access credential after use. Correspondence between the request and service data may be used to determine that the request may be processed by the receiving service and that the user device has the permissions necessary for the request to be processed. Portions of the request that meet these criteria may be provided to the service. The secure communication channel may also be used to provide the response from the service to the user device.

System for authenticating and processing service requests

Growing community of inventors

Bothell, WA, United States of America

Yu-Hsiang Cheng