Voice Input Routing via Contextual Disambiguation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing electronic devices face difficulties in determining the appropriate target application for voice inputs when multiple voice-enabled tasks coincide, requiring users to manually switch between applications, as current systems lack the ability to coordinate voice inputs in parallel.

Innovation Solution

The system employs multi-modal inputs such as eye tracking, gesture recognition, situational, and contextual data to select and route voice inputs to the appropriate active voice-enabled application, allowing multiple applications to operate in parallel without forcing users to explicitly switch between them.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If multiple voice enabled applications operate in parallel, then the system can handle multiple voice inputs simultaneously, but it becomes difficult to determine the appropriate target application for each voice input

Engineering Contradiction:

Improveparallel voice input handlingVSAvoidtarget application identification

Core Design Contradiction:

ProductivityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent introduces an intermediary system that sits between the audio receiver and multiple voice-enabled applications. This intermediary analyzes contextual information, application states, and voice input characteristics to determine which application should receive each voice input, thereby resolving the ambiguity of target identification when multiple applications are active simultaneously.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system dynamically changes parameters such as application focus state, voice input routing priorities, and contextual relevance weights based on current system conditions. By adjusting these parameters in real-time, the system can accurately route voice inputs to the appropriate application even when multiple applications are running in parallel.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If users manually switch between voice enabled applications, then the system can determine the correct target application, but this increases user effort and reduces operational efficiency

Engineering Contradiction:

Improvetarget application accuracyVSAvoiduser switching effort

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The system implements self-service by automatically determining the correct target application without requiring user intervention. The intermediary system autonomously analyzes the context and routes voice inputs to the appropriate application, eliminating the need for users to manually switch between applications while maintaining high accuracy in target identification.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system uses feedback mechanisms to continuously monitor application states and user interactions. By analyzing this feedback data, the intermediary system learns user preferences and contextual patterns, improving its ability to automatically identify the correct target application and reducing the need for manual switching over time.

Inventive Principle:

Principle #23Feedback

3Device complexity

If the system processes voice inputs serially in currently active applications, then target application determination is straightforward, but this reduces productivity when multiple voice enabled tasks coincide

Engineering Contradiction:

Improveprocessing coordinationVSAvoidvoice input throughput

Core Design Contradiction:

Device complexityVSProductivity

Solution Approach 1:

The patent segments the voice input processing system into distinct components: an audio receiver, an intermediary routing system, and multiple independent voice-enabled applications. This segmentation allows each component to operate independently and simultaneously, enabling parallel processing of multiple voice inputs while maintaining clear boundaries and coordination mechanisms between components.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The intermediary system serves multiple functions: it receives voice inputs from the audio receiver, analyzes contextual information, determines the appropriate target application, and routes the voice input accordingly. This multi-functional intermediary enables the system to handle multiple voice-enabled tasks in parallel while maintaining straightforward processing coordination through a centralized routing mechanism.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS9921805B2Multi-modal disambiguation of voice assisted input

Publication Date: 2018.03.20 LENOVO SWITZERLAND INTERNATIONAL GMBH

AI summary

One embodiment provides a method, including: receiving, at an audio receiver of a device, a voice input; selecting, using a processor of a device, an active target voice enabled resource for the voice input from among a plurality of active target voice enabled resources; and providing, using a processor of the device, the voice input to the active target voice enabled resource selected. Other aspects are described and claimed.