Audio data packet status determination

Patent metadata

Field	Value
Publication number	US-11218434-B2
Application number	US-201715584839-A
Country	US
Kind code	B2
Filing date	May 2, 2017
Priority date	Jun 12, 2013
Publication date	Jan 4, 2022
Grant date	Jan 4, 2022

Abstract

Systems and methods to determine the status of transmitted audio packets. The audio packets can include digital components that are presented by a client computing device. Based on presentation variables and determinations of presentation status, the system can generate a predictive model that can be used to dynamically determines presentation values of audio packets prior to their transmission to a client computing device.

First claim

What is claimed is:

1. A system to determine data status, the system comprising:
a data processing system including a memory and one or more processors to:
receive, from a first client computing device, a first input audio signal acquired via a sensor of the first client computing device;
parse the first input audio signal received from the first client computing device to identify a first request;
determine, using the first request, a series of actions corresponding to a series of candidate digital components;
transmit, to the first client computing device, a first output audio signal comprising a first digital component from the series of candidate digital components;
determine a presentation status of the first digital component within the first audio signal, the presentation status indicating whether the first digital component was presented via the first client computing device;
receive, from the first client computing device, first presentation variables; generate a presentation probability predictive model based on the presentation status of the first digital component, the first presentation variables, and a data set comprising prior presentation statuses and prior presentation variables determined for a plurality of client computing devices previously served an audio signal;
receive, from the first client computing device, a second input audio signal acquired via the sensor of the first client computing device and second presentation variables;
identify the second input audio signal received from the first client computing device to identify a second request;
determine a presentation value for each of a remainder in the series of candidate digital components based on the second presentation variables and the presentation probability predictive model;
determine to bypass a second digital component from the series of candidate digital components corresponding to the series of actions determined using the first request, to select a third digital component from the series of candidate digital components based on the second request and a ranking of the presentation values for each of the remainder in the series of candidate digital components; and
transmit, to the first client computing device, a second audio signal comprising the third digital component selected from the series of candidate digital components.

2. The system of claim 1 , comprising a natural language processor component to:
receive, from the first client computing device, an input audio signal, the input audio signal detected by a sensor of the first client computing device; and
parse the input audio signal into the second request and a trigger keyword.

3. The system of claim 2 , wherein the second presentation variables are based on the trigger keyword and the second request.

4. The system of claim 2 , comprising a content selector component to:
select the third digital component for transmission to the first client computing device responsive the second request and the trigger keyword.

5. The system of claim 1 , comprising a prediction component to:
determine the presentation value for each of the remainder in the series of candidate digital components based on the second presentation variables and the presentation probability predictive model;
rank the plurality of digital components based on the respective presentation values for each of the remainder in the series of candidate digital components; and
select the third digital component from the series of candidate digital components based on the ranking of the series of digital components.

6. The system of claim 1 , wherein the presentation status indicates whether a midpoint of the digital component was presented via the first client computing device.

7. The system of claim 1 , comprising the data processing system to:
determine the presentation value for the digital component based on a bid value of the digital component.

8. The system of claim 1 , comprising:
an interface to transmit data packets comprising the second audio signal to the first client computing device to cause an audio driver component executed by the first client computing device to drive a speaker to generate an accusative wave corresponding to the second audio signal.

9. The system of claim 1 , comprising the data processing system to:
determine a first bid price and a first bid type of the second digital component;
identify a candidate digital component having a second bid price greater than the first bid price and a second bid type;
determine the presentation value for the second digital component based on the second presentation variables, the presentation probability predictive model, the first bid price, and the first bid type;
determine a second value for the third candidate digital component based on the second presentation variables, the presentation probability predictive mode, the second bid price and the second bid type; and
select the third digital component for transmission to the first client computing device responsive to the ranking indicating that the presentation value is higher than the second presentation value.

10. The system of claim 1 , wherein the presentation probability predictive model determines a probability that the second digital component is played by the first client computing device past a midpoint of the digital component.

11. A method to determine data status, the method comprising:
receiving, from a first client computing device, a first input audio signal acquired via a sensor of the first client computing device;
parsing the first input audio signal received from the first client computing device to identify a first request;
determining, using the first request, a series of actions corresponding to a series of candidate digital components;
transmitting, to the first client computing device, a first output audio signal comprising a first digital component from the series of candidate digital components;
determining a presentation status of the first digital component within the first audio signal, the presentation status indicating whether the first digital component was presented via the first client computing device;
receiving, from the first client computing device, first presentation variables;
generating a presentation probability predictive model based on the presentation status of the first digital component, the first presentation variables, and a data set comprising prior presentation statuses and prior presentation variables determined for a plurality of client computing devices previously served an audio signal;
receiving, from the first client computing device, a second input audio signal acquired via the sensor of the first client computing device and second presentation variables;
identifying the second input audio signal received from the first client computing device to identify a second request;
determining a presentation value for each of a remainder in the series of candidate digital components based on the second presentation variables and the presentation probability predictive model;
determining to bypass a second digital component from the series of candidate digital components corresponding to the series of actions determined using the first request, to select a third digital component from the series of candidate digital components based on the second request and a ranking of the presentation values for each of the plurality of candidate digital components; and
transmitting, to the first client computing device, a second audio signal comprising the third digital component selected from the series of candidate digital components.

12. The method of claim 11 , comprising:

Assignees

• Google Llc

Inventors

• Ray Jonathan William
• Azmoodeh Farnaz
• Wood Eric
• Cai Congxing
• Reitsma Paul Schelte Albert
• Wilson Glenn
• Zhang Peng
• Walker Troy Louis
• Bhaya Gaurav
• Stets Robert

Classifications

• H04L51/10 Primary

  Multimedia information · CPC title

• G06F3/165

  Management of the audio stream, e.g. setting of volume, audio stream path · CPC title

• G06Q30/0254

  based on statistics · CPC title

• G10L19/167

  Audio streaming, i.e. formatting and decoding of an encoded audio signal representation into a data stream for transmission or storage purposes · CPC title

• G06F40/14

  Tree-structured documents (parsing G06F40/205; validation G06F40/226) · CPC title