Google llc (20240194190). DETECTION AND/OR ENROLLMENT OF HOT COMMANDS TO TRIGGER RESPONSIVE ACTION BY AUTOMATED ASSISTANT simplified abstract

From WikiPatents
Jump to navigation Jump to search

DETECTION AND/OR ENROLLMENT OF HOT COMMANDS TO TRIGGER RESPONSIVE ACTION BY AUTOMATED ASSISTANT

Organization Name

google llc

Inventor(s)

Yuan Yuan of Redwood City CA (US)

Bibo Xu of San Jose CA (US)

Tianyu Wang of Los Altos CA (US)

Anurag Jain of Palo Alto CA (US)

DETECTION AND/OR ENROLLMENT OF HOT COMMANDS TO TRIGGER RESPONSIVE ACTION BY AUTOMATED ASSISTANT - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240194190 titled 'DETECTION AND/OR ENROLLMENT OF HOT COMMANDS TO TRIGGER RESPONSIVE ACTION BY AUTOMATED ASSISTANT

    • Simplified Explanation:**

This patent application describes techniques for detecting and enrolling new "hot commands" that can trigger an automated assistant to perform actions without explicit invocation. The assistant can transition from a limited listening state to full speech recognition based on a trigger event. If a spoken command meets a frequency threshold in a corpus of textual commands, it can be enrolled as a hot command. Subsequent semantically consistent textual commands can then trigger responsive actions by the assistant.

    • Key Features and Innovation:**
  • Detection and enrollment of new "hot commands" for automated assistants.
  • Transition from limited listening to full speech recognition based on trigger events.
  • Enrollment of spoken commands meeting frequency thresholds in a corpus of textual commands.
  • Triggering of responsive actions by the assistant based on subsequent semantically consistent textual commands.
    • Potential Applications:**

This technology could be applied in various automated assistant systems, such as smart speakers, virtual assistants, and chatbots.

    • Problems Solved:**
  • Streamlining the process of enrolling new commands for automated assistants.
  • Allowing for responsive actions without explicit invocation by users.
    • Benefits:**
  • Improved user experience with automated assistants.
  • Increased efficiency in performing tasks through voice commands.
  • Enhanced functionality of automated assistant systems.
    • Commercial Applications:**

Potential commercial applications include smart home devices, customer service chatbots, and virtual personal assistants. This technology could enhance user interactions with these systems, leading to increased customer satisfaction and loyalty.

    • Prior Art:**

Prior art related to this technology may include research on speech recognition systems, natural language processing, and automated assistant technologies.

    • Frequently Updated Research:**

Ongoing research in the field of artificial intelligence and natural language processing may impact the development and implementation of this technology. Stay updated on advancements in speech recognition and automated assistant systems for potential improvements and innovations.

    • Questions about Hot Commands:**

1. How does the enrollment of hot commands improve the user experience with automated assistants? 2. What are the potential challenges in detecting and enrolling new hot commands for automated assistants?


Original Abstract Submitted

techniques are described herein for detecting and/or enrolling (or commissioning) new “hot commands” that are useable to cause an automated assistant to perform responsive action(s) without having to be first explicitly invoked. in various implementations, an automated assistant may be transitioned from a limited listening state into a full speech recognition state in response to a trigger event. while in the full speech recognition state, the automated assistant may receive and perform speech recognition processing on a spoken command from a user to generate a textual command. the textual command may be determined to satisfy a frequency threshold in a corpus of textual commands. consequently, data indicative of the textual command may be enrolled as a hot command. subsequent utterance of another textual command that is semantically consistent with the textual command may trigger performance of a responsive action by the automated assistant, without requiring explicit invocation.