Activation of remote devices in a networked system

Patent metadata

Field	Value
Publication number	US-11145300-B2
Application number	US-201816064961-A
Country	US
Kind code	B2
Filing date	May 7, 2018
Priority date	May 7, 2018
Publication date	Oct 12, 2021
Grant date	Oct 12, 2021

Abstract

The present disclosure is generally directed to the generation of voice-activated data flows in interconnected network. The voice-activated data flows can include input audio signals that include a request and are detected at a client device. The client device can transmit the input audio signal to a data processing system, where the input audio signal can be parsed and passed to the data processing system of a service provider to fulfill the request in the input audio signal. The present solution is configured to conserve network resources by reducing the number of network transmissions needed to fulfill a request.

First claim

The invention claimed is:

1. A system to generate voice-activated threads in a networked computer environment, comprising:
a data processing system comprising one or more processors and memory, the one or more processors executing a natural language processor, a remote application launcher, and an action handler component to:
receive, by the natural language processor component, a first input audio signal detected by a sensor of a first client computing device;
parse, by the natural language processor component, the first input audio signal to identify a first request and a first entity;
determine, a plurality of candidate service provider devices, each of the plurality of candidate service provider devices configured to fulfill the first request and associated with a respective application installed on the first client computing device;
select, by the action handler component, a service provider device from the plurality of candidate service provider devices;
expand, by the action handler component, a second entity of the first input audio signal into a format associated with a field of a digital component based on an expansion policy associated with the first client computing device;
generate, by the remote application launcher, the digital component comprising an indication of an application associated with the service provider device and the first entity, the digital component configured to launch the application associated with the service provider device when executed by the first client computing device to fulfill the first request; and
transmit, by the action handler component, the digital component to the first client computing device in response to the first input audio signal.

2. The system of claim 1 , comprising:
the natural language processor component to parse the first input audio signal to identify the second entity; and
the action handler component to:
generate the digital component to include the expanded second entity in the field of the digital component.

3. The system of claim 1 , wherein the digital component is configured to populate a field of the application associated with the service provider device with the first entity when executed by the first client computing device.

4. The system of claim 1 , comprising the action handler component to:
measure a network latency between the data processing system and each of the plurality of candidate service provider devices; and
select the service provider device from the plurality of candidate service provider devices based at least on the network latency between the data processing system and each of the plurality of candidate service provider devices.

5. The system of claim 1 , comprising:
the action handler component to select the service provider device from the plurality of candidate service provider devices based at least on a performance of each of the plurality of candidate service provider devices.

6. The system of claim 1 , comprising:
the action handler component to select the service provider device from the plurality of candidate service provider devices based at least on a preference associated with the first client computing device.

7. The system of claim 1 , comprising:
the natural language processor component to receive a second input audio signal detected by the sensor of the first client computing device, the second input audio signal comprising an indication of the service provider device; and
the action handler component to select the service provider device from the plurality of candidate service provider devices based at least on the indication of the service provider device.

8. The system of claim 1 , comprising:
the natural language processor component to:
receive a second input audio signal detected by the sensor of the first client computing device;
parse the second input audio signal to identify a second request and a second entity; and
the action handler component to:
determine the service provider device is configured to fulfill the second request;
generate a first action data structure based on the second request and comprising the second entity; and
transmit the first action data structure to the service provider device.

9. A method to generate voice-activated threads in a networked computer environment, comprising:
receiving, by a natural language processor component executed by a data processing system, a first input audio signal detected by a sensor of a first client computing device;
parsing, by the natural language processor component, the first input audio signal to identify a first request, a first entity, and a second entity;
identifying, by an action handler component executed by the data processing system, a plurality of candidate service provider devices, each of the plurality of candidate service provider devices configured to fulfill the first request and associated with a respective application installed on the first client computing device;
selecting, by the action handler component, a service provider device from the plurality of candidate service provider devices;
expanding, by the action handler component executed by the data processing system, the second entity based on an expansion policy associated with the first client computing device and into a format associated with a field of a digital component;
generating, by a remote application launcher executed by the data processing system, the digital component comprising an indication of an application associated with the service provider device, the first entity, and the expanded second entity in the field of the digital component, the digital component configured to launch the application associated with the service provider device when executed by the first client computing device to fulfill the first request; and
transmitting, by the action handler component, the digital component to the first client computing device in response to the first input audio signal.

10. A method to generate voice-activated threads in a networked computer environment, comprising:
receiving, by a natural language processor component executed by a data processing system, a first input audio signal detected by a sensor of a first client computing device;
parsing, by the natural language processor component, the first input audio signal to identify a first request, a first entity, and a second entity;
identifying, by an action handler component executed by the data processing system, a plurality of candidate service provider devices, each of the plurality of candidate service provider devices configured to fulfill the first request and associated with a respective application installed on the first client computing device;
selecting, by the action handler component, a service provider device from the plurality of candidate service provider devices;
determining, by the action handler component, the second entity cannot be expanded based on an expansion policy associated with the first client computing device;
generating, by a remote application launcher executed by the data processing system, a digital component comprising an indication of an application associated with the service provider device and the first entity, the digital component configured to launch the application associated with the service provider device when executed by the first client computing device to fulfill the first request; and
transmitting, by the action handler component, the digital component to the first client computing device in response to the first input audio signal.

11. The method of claim 9 , wherein the digital component is configured to populate a field of the application associated with the service provider devic

Assignees

• Google Llc

Inventors

• Bhaya Gaurav
• Kirazci Ulas
• Abrams Bradley
• Coimbra Adam
• Firman Ilya
• Radebaugh Carey

Classifications

• G06F40/216

  using statistical methods · CPC title

• G06F40/35

  Discourse or dialogue representation · CPC title

• G10L15/30

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G06F16/9027

  Trees · CPC title