Digital assistant voice input integration

Patent metadata

Field	Value
Publication number	US-10147421-B2
Application number	US-201414572184-A
Country	US
Kind code	B2
Filing date	Dec 16, 2014
Priority date	Dec 16, 2014
Publication date	Dec 4, 2018
Grant date	Dec 4, 2018

Abstract

A digital assistant supported on devices such as smartphones, tablets, personal computers, game consoles, etc. includes an extensibility client that exposes an interface and service that enables third party applications to be integrated with the digital assistant so the application user experiences are rendered using the native voice of the digital assistant. Specific voice inputs associated with a given application may be registered by developers using a manifest that is loaded when the application is launched on the device so that voice inputs from the device user can be mapped by the digital assistant extensibility client to the appropriate application as input events for consumption. In typical implementations, the manifest is arranged as a declarative document that streamlines application development and provides a seamless user experience by enabling customization of third party applications to integrate the digital assistant's voice and behaviors within the user experience of the application's domain.

First claim

What is claimed:

1. has been amended as:
A device, comprising:
one or more processors;
a user interface (UI) for interacting with a user of the device using graphics and audio; and
a memory device storing code associated with one or more applications and computer-readable instructions which, when executed by the one or more processors, perform a method comprising the steps of:
exposing a digital assistant on the device configured for maintaining context-awareness for a device user by monitoring user behaviors and interactions with the device, the digital assistant further interacting with the device user using voice interactions through the UI, the one or more applications each being distinct from the digital assistant,
registering, after launch and during runtime of an application from the one or more applications, a plurality of manifests of commands with the digital assistant, wherein respective manifests of commands are application-specific with respective applications among a plurality of applications currently in runtime from the one or more applications;
listening for voice commands from the device user,
determining, at the digital assistant and after receiving a voice command, which of the plurality of applications to direct the voice command according to;
the application-specific manifests of commands, and
the context awareness, and
delivering the voice command to the determined application for handling,
wherein, after receiving the delivered voice command, the determined application handles operations associated with the voice command and controls the digital assistant to provide voice output to the user that is responsive to the user's voice command.

2. The device of claim 1 further including enabling the one or more applications to opt in to digital assistant extensibility services surfaced by a local client operating on the device.

3. The device of claim 1 further including enabling the one or more applications to load application-specific voice commands from a manifest into a runtime environment for execution.

4. The device of claim 3 in which the manifest is populated using declarative markup.

5. The device of claim 4 further including mapping instances of the application-specific voice commands to the applications for consumption as input events.

6. has been amended as follows:
The device of claim 1 in which the determined application parses one or more chunks of text for the digital assistant to read aloud using the digital assistant's native voice.

Assignees

• Microsoft Technology Licensing Llc
• Microcoft Tech Licensing Llc

Inventors

• Liddell Derek
• Zhou Francis
• Yen Cheng-Yi

Classifications

• G10L15/24

  Speech recognition using non-acoustical features · CPC title

• G10L13/033

  Voice editing, e.g. manipulating the voice of the synthesiser · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L2015/228

  of application context · CPC title

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title