Audio based entity-action pair based selection

Patent metadata

Field	Value
Publication number	US-2021286844-A1
Application number	US-202117327184-A
Country	US
Kind code	A1
Filing date	May 21, 2021
Priority date	May 31, 2013
Publication date	Sep 16, 2021
Grant date	—

Abstract

Routing packetized actions in a voice activated data packet based computer network environment is provided. A system can receive audio signals detected by a microphone of a device. The system can parse the audio signal to identify trigger keyword and request, and generate an action data structure. The action data structure can include digital components and entity-action pairs.

First claim

1 .- 20 . (canceled)

21 . A system to transmit packetized data in voice-activated computer environments, comprising:
a data processing system having one or more processors coupled with memory to:
identify, from an input audio signal acquired via a microphone of a client device, a request to perform at least one of a first action associated with a first entity or a second action associated with a second entity;
determine, based on the request, a first entity-action pair and a second entity-action pair, the first entity-action pair the identifying the first entity and the first action to performed in relation to the first entity, the second entity-action pair identifying the second entity and the second action in relation to the second entity;
identify a first content item based on the first entity-action pair and a second content item based on the second entity-action pair; and
provide, to the client device, an output audio signal comprising at least one of the first content item or the second content item.

22 . The system of claim 21 , comprising the data processing system to provide, to a service provider associated with an entity corresponding to at least one of the first entity or the second entity, an entity-pair corresponding to at least one of the first entity-pair action or the second entity-pair action, to invoke the service provider to invoke a interface with the client device.

23 . The system of claim 21 , comprising the data processing system to provide, to a service provider associated with an entity corresponding to at least one of the first entity or the second entity, an action data structure including an entity-action pair to invoke the service provider to carry out an action identified by the entity-action pair.

24 . The system of claim 21 , comprising the data processing system to route, to service provider associated with at least one of the first entity or the second entity, a second request identified from a second input audio signal acquired via the microphone of the client device, subsequent to selection at least one of the first entity or the second entity.

25 . The system of claim 21 , comprising the data processing system to
identify, from the input audio signal, a trigger keyword corresponding to the request to perform at least one of the first action associated with the first entity or the second action associated with the second entity; and identify, using the trigger keyword, a first service provider associated with the first entity to perform the first action and a second service provider associated with the second entity to perform the second action.

26 . The system of claim 21 , comprising the data processing system to determine, based on a search result identified using the request, the first entity associated with the first action and the second entity associated with the second action.

27 . The system of claim 21 , comprising the data processing system to determine, based on the request, a first identifier corresponding to the first entity and the first action and a second identifier corresponding to the second entity and the second action.

28 . The system of claim 21 , comprising the data processing system to:
determine, based on the request, a first score for the first entity associated with the first action and a second score for the second entity associated with the second action; and select at least one of the first entity-action pair or the second entity-action pair based on the first score and the second score.

29 . The system of claim 21 , comprising the data processing system to:
determine a first score for the first content item and a second score for the second content item; and select at least one of the first content item or the second content item to provide to the client device based on the first score and the second score.

30 . The system of claim 21 , comprising the data processing system to select at least one of the first content item or the second content item to provide to the client device in accordance with a content selection process.

31 . A method of data transmission in a voice activated computer network environment, comprising:
identifying, by a data processing system, from an input audio signal acquired via a microphone of a client device, a request to perform at least one of a first action associated with a first entity or a second action associated with a second entity; determining, by the data processing system, based on the request, a first entity-action pair and a second entity-action pair, the first entity-action pair the identifying the first entity and the first action to performed in relation to the first entity, the second entity-action pair identifying the second entity and the second action in relation to the second entity; identifying, by the data processing system, a first content item based on the first entity-action pair and a second content item based on the second entity-action pair; and transmitting, by the data processing system, to the client device, an output audio signal comprising at least one of the first content item or the second content item.

32 . The method of claim 31 , comprising providing, by the data processing system, to a service provider associated with an entity corresponding to at least one of the first entity or the second entity, an entity-pair corresponding to at least one of the first entity-pair action or the second entity-pair action, to invoke the service provider to invoke a interface with the client device.

33 . The method of claim 31 , comprising providing, by the data processing system, to a service provider associated with an entity corresponding to at least one of the first entity or the second entity, an action data structure including an entity-action pair to invoke the service provider to carry out an action identified by the entity-action pair.

34 . The method of claim 31 , comprising transmitting, by the data processing system, to service provider associated with at least one of the first entity or the second entity, a second request identified from a second input audio signal acquired via the microphone of the client device, subsequent to selection at least one of the first entity or the second entity.

35 . The method of claim 31 , comprising:
identifying, by the data processing system, from the input audio signal, a trigger keyword corresponding to the request to perform at least one of the first action associated with the first entity or the second action associated with the second entity; and identifying, by the data processing system, using the trigger keyword, a first service provider associated with the first entity to perform the first action and a second service provider associated with the second entity to perform the second action.

36 . The method of claim 31 , comprising determining, by the data processing system, based on a search result identified using the request, the first entity associated with the first action and the second entity associated with the second action.

37 . The method of claim 31 , comprising determining, by the data processing system, based on the request, a first identifier corresponding to the first entity and the first action and a second identifier corresponding to the second entity and the second action.

38 . The method of claim 31 , comprising:
determining, by the data processing system, based on the request, a first score for the first entity associated with the first action and a second score for the second entity associated with the second act

Assignees

• Google Llc

Inventors

• Collins Alexander
• Leader Ian James
• Zhou Yunkai
• Bhaya Gaurav
• Stets Robert

Classifications

• G06F16/632 Primary

  Query formulation · CPC title

• G10L2015/088

  Word spotting · CPC title

• G06F16/951

  Indexing; Web crawling techniques · CPC title

• G10L15/08

  Speech classification or search · CPC title

• G10L25/54

  for retrieval · CPC title