Voice Action Discoverability Platform
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users of software applications often lack knowledge of the commands required to trigger specific actions, leading to difficulties in interacting with applications through voice inputs, as existing systems do not effectively provide discoverability of available voice actions and their usage contexts.
Innovation Solution
A platform that allows application developers to deploy new voice actions and provide discoverability examples, enabling users to understand how to trigger these actions by specifying trigger terms, contexts, and presenting notifications such as textual, image, or audio cues based on the application's status, allowing users to interact with applications using voice commands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If voice actions are added to applications, then functionality and user interaction capabilities are improved, but user knowledge requirements and interaction complexity increase
Solution Approach 1:
The system performs preliminary action by proactively presenting discoverability examples to users before they need to use voice commands. The platform automatically generates and displays contextual information about available voice actions based on the current application state, so users are informed of commands they can use without having to search or remember them.
Solution Approach 2:
The system implements feedback by continuously monitoring application context and user interactions, then providing relevant discoverability information about voice actions. The platform analyzes the current application state and delivers targeted feedback to users about which voice commands are available and appropriate in the current context, creating a closed-loop information system.
2Ease of operation
If discoverability examples are provided to users, then ease of operation is improved, but information processing requirements and system complexity increase
Solution Approach 1:
The platform implements universality by creating a multi-functional system that simultaneously performs context analysis, voice action matching, discoverability example generation, and delivery across different applications. The same core platform infrastructure serves multiple applications and contexts, reducing overall system complexity through shared components rather than separate specialized systems for each function.
Solution Approach 2:
The system applies self-service by automatically analyzing application context and generating appropriate discoverability examples without requiring manual configuration or intervention. The platform autonomously monitors application state, identifies relevant voice actions, and presents information to users, making the system self-sufficient in providing guidance while minimizing the need for external configuration.
Data Source
AI summary
Methods, systems, and apparatus for receiving, by a voice action system, data specifying trigger terms that trigger an application to perform a voice action and a context that specifies a status of the application when the voice action can be triggered. The voice action system receives data defining a discoverability example for the voice action that comprises one or more of the trigger terms that trigger the application to perform the voice action when a status of the application satisfies the specified context. The voice action system receives a request for discoverability examples for the application from a user device having the application installed, and provides the data defining the discoverability examples to the user device in response to the request. The user device is configured to provide a notification of the one or more of the trigger terms when a status of the application satisfies the specified context.