Voice Action System for Deploying New Application Commands

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing voice action systems lack the ability to deploy new voice actions for previously installed software applications without modifying the application code, limiting user interaction and functionality.

Innovation Solution

A platform that allows application developers to submit information defining new voice actions, including the application, trigger terms, and context for triggering these actions, which are validated and converted into a specific intent format, enabling deployment without altering existing application code.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If voice actions are added to existing applications by modifying application code, then the functionality and user interaction are enhanced, but the complexity of deployment and maintenance increases

Engineering Contradiction:
Improvefunctionality enhancementVSAvoiddeployment complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent introduces a voice action system that acts as an intermediary layer between the user and the application. This system includes a voice input interface, speech recognition module, and action execution module that can interpret voice commands and translate them into application operations without requiring modifications to the application code itself. The system mediates between voice input and application functionality, allowing existing applications to gain voice control capabilities through an external layer.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The voice action system is designed as a universal platform that can work with multiple different applications simultaneously. The system defines a standardized interface and protocol that allows various applications to be controlled through voice commands without requiring application-specific modifications. This multi-functional approach enables a single voice control system to serve multiple applications across different contexts and user needs.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Ease of manufacture

If voice actions are deployed without modifying application code, then deployment complexity is reduced, but the precision of voice command execution and context understanding may be limited

Engineering Contradiction:
Improvedeployment easeVSAvoidvoice command execution precision
Core Design Contradiction:
Ease of manufactureVSManufacturing precision

Solution Approach 1:

The system performs preliminary actions by pre-defining voice actions with their associated contexts, triggers, and operations in a structured format. The voice action system includes a configuration module that allows developers to specify the conditions under which voice commands should be recognized and executed. This preliminary configuration enables the system to understand application context and execute commands with high precision without requiring real-time code modifications.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The voice action system is designed to be dynamic and adaptive, allowing it to learn from usage patterns and improve its context understanding over time. The system can dynamically adjust its speech recognition parameters, context matching criteria, and command routing based on observed usage patterns. This dynamic adaptation enables the system to maintain high execution precision while working with diverse applications without code modifications.

Inventive Principle:
Principle #15Dynamics

3Reliability

If a centralized system validates and deploys voice actions, then system reliability and consistency are improved, but the time required to deploy new voice actions increases

Engineering Contradiction:
Improvesystem consistencyVSAvoiddeployment time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The centralized voice action system performs validation and configuration of voice actions in advance, before they are deployed to users. The system includes a validation module that checks voice action definitions for correctness, consistency, and compatibility with target applications. By performing these checks preliminarily, the system ensures reliable and consistent deployment without requiring time-consuming validation processes to occur during actual deployment to end users.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The centralized system creates standardized templates and copies of validated voice action configurations that can be rapidly deployed across multiple applications and users. Once a voice action is validated and configured correctly in the centralized system, it can be copied and instantiated multiple times without requiring re-validation. This copying mechanism maintains system consistency and reliability while significantly reducing the time required to deploy voice actions to multiple targets.

Inventive Principle:
Principle #26Copying

Data Source

PatentEP3424045B1Developer voice actions system
Publication Date: 2020.09.23 GOOGLE LLC
  • EP3424045B1 patent drawingFigure 1
  • EP3424045B1 patent drawingFigure 2
  • EP3424045B1 patent drawingFigure 3

AI summary

Methods, systems, and apparatus for receiving, by a voice action system, data specifying a new voice action for an application different from the voice action system. A voice action intent for the application is generated based at least on the data, wherein the voice action intent comprises data that, when received by the application, requests that the application perform one or more operations specified for the new voice action. The voice action intent is associated with trigger terms specified for the new voice action. The voice action system is configured to receive an indication of a user utterance obtained by a device having the application installed, and determines that a transcription of the user utterance corresponds to the trigger terms associated with the voice action intent. In response to the determination, the voice action system provides the voice action intent to the device.