Secondary transmissions of packetized data

• US 20170257456A1
• Filed: 05/24/2017
• Published: 09/07/2017
• Est. Priority Date: 01/31/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Vaish, Vaibhav, Ramachandran, Venky, Sisson, David Philip, Kandhan, Ramakrishnan, Adiddam, Pramod, Marur, Vinod, Garg, Gaurav, Bhaya, Gaurav, Stets, Robert
• Granted Patent: US 10,735,552 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: H04L 43/08 Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
• CPC Class Codes: H04L 67/01 Protocols
• CPC Class Codes: H04L 67/60 Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources admission control or resource allocation H04L47/70

Abstract

A system for transmission of packetized data in a voice activated computer network environment. The system can identify candidate canonicalized digital components that relate to secondary search locations. For each of the candidate canonicalized digital components the system can calculate transmissions scores that are used to select one of the candidate canonicalized digital components for transmission.

Claims

1-34. -34. (canceled)

35. A system to transmit packetized data in a voice activated computer network environment, the system comprising a data processing system having a processor and a memory to:

receive, via an interface, data packets comprising an input audio signal detected by a sensor of a client computing device;

identify a first request within the input audio signal detected by the sensor of the client computing device;

determine, based on the first request, a primary search result having a primary digital component and a secondary search result URL related to the primary search result;

identify a plurality of candidate canonicalized digital components associated with the secondary search result URL;

determine a respective score for each of the plurality of candidate canonicalized digital components;

select one of the plurality of candidate canonicalized digital components based on the respective score for each of the plurality of candidate canonicalized digital components and a filter rule;

transmit a primary output audio signal comprising the primary digital component; and

transmit a secondary output signal comprising the one of the plurality of candidate canonicalized digital components.

36. The system of claim 35, comprising a natural language processor component to:

receive the data packets comprising the input audio signal; and

parse the input audio signal to identify the first request and a trigger keyword.

37. The system of claim 36, comprising a content selector component to:

receive the first request and the trigger keyword; and

select the primary digital component based on the first request and the trigger keyword via a real-time content selection process.

38. The system of claim 35, wherein the selected one of the plurality of candidate canonicalized digital components comprises a URL to a video-based digital component.

39. The system of claim 38, comprising the data processing system to:

transmit the secondary output signal to a second client computing device different than the first client computing device.

40. The system of claim 35, comprising an interface management component to:

poll a plurality of interfaces to identify a first candidate interface and a second candidate interface;

determine a first attribute of the primary digital component and a second attribute of the selected on of the plurality of candidate canonicalized digital components;

determine a first resource utilization value of the first candidate interface and a second resource utilization value of the second candidate interface;

select the first candidate interface as the primary interface based on a comparison of the first resource utilization value and the second resource utilization value; and

select the second candidate interface as the secondary interface based on the comparison of the first resource utilization value and the second resource utilization.

41. The system of claim 40, wherein the interface management comparison:

transmits the primary output audio signal to the primary interface; and

transmits the secondary output audio signal to the secondary interface.

42. The system of claim 40, wherein the interface management component:

determines the first resource utilization value of the first candidate interface based on at least one of a battery status, a processor utilization, a memory utilization, an interface parameter, or a bandwidth utilization of the first candidate interface; and

determines the second resource utilization value of the second candidate interface based on at least one of a battery status, a processor utilization, a memory utilization, an interface parameter, or a bandwidth utilization of the second candidate interface.

43. The system of claim 35, wherein the respective score for each of the plurality of canonicalized digital components is based on a term frequency within each of the plurality of candidate canonicalized digital components.

44. The system of claim 35, wherein the filter rules include at least one of a language rule, a geographic rule, a user device rule, and a platform rule.

45. A method of data transmission in a voice activated computer network environment, comprising:

receiving, via an interface, data packets comprising an input audio signal detected by a sensor of a client computing device;

identifying a first request within the input audio signal detected by the sensor of the client computing device;

determining, based on the first request, a primary search result having a primary digital component and a secondary search result URL related to the primary search result;

identifying a plurality of candidate canonicalized digital components associated with the secondary search result URL;

calculating a respective score for each of the plurality of candidate canonicalized digital components;

selecting one of the plurality of candidate canonicalized digital components based on the respective score for each of the plurality of candidate canonicalized digital components and a filter rule;

transmitting a primary output audio signal comprising the primary digital component; and

transmitting a secondary output signal comprising the selected one of the plurality of candidate canonicalized digital components.

46. The method of claim 45, comprising:

receiving, by a natural language processor component, the data packets comprising the input audio signal; and

parsing, by the natural language processor component, the input audio signal to identify the first request and a trigger keyword.

47. The method of claim 46, comprising:

receiving, by a content selector component, the first request and the trigger keyword; and

selecting, by the content selector component, the primary digital component based on the first request and the trigger keyword via a real-time content selection process.

48. The method of claim 45, wherein the selected one of the plurality of candidate canonicalized digital components comprises a URL to a video-based digital component.

49. The method of claim 48, comprising:

transmitting the secondary output signal to a second client computing device different than the first client computing device.

50. The method of claim 45, comprising:

polling, by an interface management component, a plurality of interfaces to identify a first candidate interface and a second candidate interface;

determining, by the interface management component, a first attribute of the primary digital component and a second attribute of the selected on of the plurality of candidate canonicalized digital components;

determining, by the interface management component, a first resource utilization value of the first candidate interface and a second resource utilization value of the second candidate interface;

selecting, by the interface management component, the first candidate interface as the primary interface based on a comparison of the first resource utilization value and the second resource utilization value; and

selecting, by the interface management component, the second candidate interface as the secondary interface based on the comparison of the first resource utilization value and the second resource utilization.

51. The method of claim 50, comprising:

transmitting, by the interface management component, the primary output audio signal to the primary interface; and

transmitting, by the interface management component, the secondary output audio signal to the secondary interface.

52. The method of claim 50, comprising:

determining, by the interface management component, the first resource utilization value of the first candidate interface based on at least one of a battery status, a processor utilization, a memory utilization, an interface parameter, or a bandwidth utilization of the first candidate interface; and

determining, by the interface management component, the second resource utilization value of the second candidate interface based on at least one of a battery status, a processor utilization, a memory utilization, an interface parameter, or a bandwidth utilization of the second candidate interface.

53. The method of claim 45, comprising:

calculating the score for each of the plurality of candidate canonicalized digital components based on a term frequency within each of the plurality of candidate canonicalized digital components.

54. The method of claim 45, comprising:

filtering the plurality of candidate canonicalized digital components based on at least one of a language rule, a geographic rule, a user device rule, and a platform rule.