公开(公告)号：US11508372B1

公开(公告)日：2022-11-22

申请号：US16904853

申请日：2020-06-18

Applicant: Amazon Technologies, Inc.

Inventor： Michael Schwartz ,  Joe Pemberton ,  Steven Mack Saunders ,  Archit Jain ,  Alexander Go

IPC: G06F40/30 ,  G10L15/22 ,  G10L15/18 ,  G06N20/20 ,  G10L15/06 ,  G10L15/183 ,  G06F40/35 ,  G06F40/295 ,  G06F16/332

Abstract: Techniques for performing runtime ranking of skill components are described. A skill developer may generate a rule indicating a skill component is to be invoked at runtime when a natural language input corresponds to a specific context. At runtime, a virtual assistant system may implement a machine learned model to generate an initial ranking of skill components. Thereafter, the virtual assistant system may use skill component-specific rules to adjust the initial ranking, and this second ranking is used to determine which skill component to invoke to respond to the natural language input. Overtime, if a rule results in beneficial user experiences, the virtual assistant system may incorporate the rule into the machine learned model.

公开(公告)号：US12205580B1

公开(公告)日：2025-01-21

申请号：US17036617

申请日：2020-09-29

Applicant: Amazon Technologies, Inc.

Inventor： Joe Pemberton ,  Michael Schwartz ,  Vijitha Raji ,  Archit Jain ,  Tara Raj ,  Alexander Go

IPC: G10L15/22

Abstract: Techniques for selecting a skill component to process a natural language input are described. When a natural language input is received, natural language understanding (NLU) output data representing the natural language input is generated, and skill components (capable of processing the NLU output data) are determined. Thereafter, rules (for preventing the invocation of skill components) are implemented in a tiered manner, resulting in the determination of a subset of the skill components. The subset of skill components is ranked using a machine learning model(s), and the top-ranked skill component is called to process the NLU output data.