Speech Recognition Context Switching via Filtered Menus

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current navigation methods between different user interfaces in applications, such as video games, are cumbersome and lack efficiency, particularly in switching between various interaction contexts and functionalities.

Innovation Solution

Implementing speech recognition techniques that allow users to switch between different contexts and user interfaces via speech commands, using a context menu that lists available contexts filtered by specific criteria, which can be navigated through voice inputs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional menu-driven navigation is used to switch between user interfaces, then the application can provide multiple contexts and functionalities, but the navigation process becomes cumbersome and time-consuming

Engineering Contradiction:
Improvecontext switching capabilityVSAvoidnavigation time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent replaces manual navigation mechanics (clicking through menus, navigating interfaces) with speech recognition technology. Users can switch between contexts by speaking commands like 'show me the settings' or 'go to multiplayer', which are converted into navigation actions by the speech recognition system, eliminating the need for manual menu traversal.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The speech recognition system acts as an intermediary between the user and the application's context switching mechanism. Instead of directly interacting with menu structures, users speak natural language commands that the speech recognition system interprets and translates into context switching operations, providing a more efficient navigation path.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If a context menu with multiple options is provided for navigation, then users can access various functionalities, but the interface complexity increases

Engineering Contradiction:
Improvecontext accessibilityVSAvoidinterface complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent replaces complex visual menu interfaces with speech-based navigation. Instead of presenting users with layered menus and requiring them to navigate through multiple levels, the system accepts speech commands that directly access the desired context, effectively replacing the mechanical menu navigation system with a more efficient speech recognition system.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The navigation system is segmented into distinct speech-recognized contexts or modes. Each context (settings, multiplayer, single-player, etc.) is treated as a separate recognizable entity that can be directly accessed through specific speech commands, rather than requiring users to navigate through a unified complex menu structure.

Inventive Principle:
Principle #1Segmentation

3Reliability

If manual navigation through user interfaces is required, then precise control over context switching is achieved, but ease of operation decreases

Engineering Contradiction:
Improvecontext switching precisionVSAvoidnavigation convenience
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The patent substitutes manual pointing and clicking mechanics with speech-based interaction. Users can switch contexts by speaking natural language commands, which are recognized and executed by the speech recognition system, providing both precision (through accurate speech recognition) and ease of operation (through natural speech input).

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The speech recognition system provides self-service by automatically interpreting speech commands and executing the appropriate context switching operations without requiring users to manually navigate through interfaces. The system serves itself by converting spoken commands directly into navigation actions, reducing the operational burden on users.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP2766791B1Speech recognition for context switching
Publication Date: 2017.05.31 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP2766791B1 patent drawingFigure 1
  • EP2766791B1 patent drawingFigure 2
  • EP2766791B1 patent drawingFigure 3

AI summary

Various embodiments provide techniques for implementing speech recognition for context switching. In at least some embodiments, the techniques can enable a user to switch between different contexts and/or user interfaces of an application via speech commands. In at least some embodiments, a context menu is provided that lists available contexts for an application that may be navigated to via speech commands. In implementations, the contexts presented in the context menu include a subset of a larger set of contexts that are filtered based on a variety of context filtering criteria. A user can speak one of the contexts presented in the context menu to cause a navigation to a user interface associated with one of the contexts.