US 10,950,231 B1Granted

Skill enablement

AssigneeAmazon Technologies, Inc.

InventorsMark Conrad Kockerbeck, John Peach, Kevin Boehm, Tina Orooji, Ian Christopher Suttle, Robert Pulciani

Life of this patent

Estimating the term…

Loading patent…

Abstract

Techniques for selecting a skill, to respond to a user input, using skill rankings are described. A skill's ranking may be determined in different manners. In one example, a skill's ranking may be determined based on a number of different users inputting commands that invoke the skill over a period of time. In another example, a skill's ranking may be determined based on a number of different devices that capture user inputs that invoke the skill over a period of time. A system may determine whether to automatically enable a skill (e.g., without user input received after the original user input), or ask the user whether the skill should be enabled, based on the skill's ranking. Moreover, a system may use a skill's ranking to determine whether to interact with a user, to enable the skill, using a graphical user interface or a voice user interface.

Claims20

Dependent claims

A method, comprising:

receiving, from a first device, audio data representing a user input;
performing automatic speech recognition (ASR) processing on the audio data to generate text data;
performing natural language understanding (NLU) processing on the text data to generate NLU results data;
determining a first skill is configured to execute with respect to the NLU results data;
determining a second skill is configured to execute with respect to the NLU results data;
determining the first skill corresponds to a first category, the first category representing a number of user identifiers, which have caused the first skill to be invoked within a past period of time;
determining the first category satisfies a first condition;
determining the second skill corresponds to a second category;
selecting the first skill based at least in part on comparing the first category and the second category;
determining user profile data associated with the audio data;
determining the first skill is missing from a list of enabled skills represented in the user profile data;
determining the first category satisfies a second condition;
based at least in part on the first category satisfying the second condition, storing first data indicating the first skill is enabled with respect to the user profile data;
and
sending at least a portion of the NLU results data to a second device associated with the first skill.

12 more elements

A system, comprising:

at least one processor;
and
at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:
receive, from a device, first data representing a user input;
generate natural language understanding (NLU) results data representing the first data;
determine a skill configured to execute with respect to the NLU results data;
determine the skill corresponds to a category, the category representing a trustworthiness of the skill, the category to be used to determine how the skill is to be enabled with respect to a user profile;
determine user profile data associated with the first data;
determine the skill is missing from a list of enabled skills represented in the user profile data;
and
determine an enablement process for the skill based at least in part on the category.

8 more elements

Dependencies are inferred from the claim text.