Wearable Speech Context Processing via Modular Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current software applications lack the ability to effectively process speech input in a wearable computing device by determining context based on historical data and databases to generate relevant actions or search requests, limiting their functionality in providing accurate and efficient outputs.

Innovation Solution

A wearable computing device receives speech input, converts it to text, and determines context using accessed documents and databases to evaluate actions, which can include commands or search requests, and generates appropriate outputs, such as communicating search requests to a search engine and providing results.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If speech input processing is implemented in wearable computing devices using traditional software applications, then basic speech-to-text conversion can be achieved, but the system cannot effectively determine context based on historical data and databases to generate relevant actions or search requests

Engineering Contradiction:
Improvecontext-based speech processing capabilityVSAvoidsoftware application structure
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the speech processing system into distinct functional modules: speech-to-text conversion module, context determination module (accessing historical documents and databases), action evaluation module, and output generation module. This segmentation allows each module to specialize in specific tasks, improving adaptability while managing complexity through modular design.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by pre-accessing and storing historical documents and database information before speech processing occurs. The context determination module prepares relevant historical data and database queries in advance, enabling faster and more accurate context-based speech processing when actual speech input is received.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If the wearable device integrates historical data and database information for context determination, then speech processing accuracy and relevance are improved, but the processing time and computational resources increase

Engineering Contradiction:
Improvespeech context determination accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system applies partial action by selectively accessing only the most relevant portions of historical documents and databases based on the speech input context, rather than processing all available data. The action evaluation module evaluates and prioritizes which context elements to use, reducing processing time while maintaining accuracy.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The system implements feedback mechanisms where the action evaluation module continuously refines context determination based on the relevance and accuracy of retrieved historical data and database information. This feedback loop allows the system to learn from previous processing outcomes, improving accuracy over time while optimizing processing efficiency.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS9911418B2Systems and methods for speech command processing
Publication Date: 2018.03.06 GOOGLE LLC
  • US9911418B2 patent drawing
  • US9911418B2 patent drawing
  • US9911418B2 patent drawing

AI summary

Methods and apparatus related to processing speech input at a wearable computing device are disclosed. Speech input can be received at the wearable computing device. Speech-related text corresponding to the speech input can be generated. A context can be determined based on database(s) and/or a history of accessed documents. An action can be determined based on an evaluation of at least a portion of the speech-related text and the context. The action can be a command or a search request. If the action is a command, then the wearable computing device can generate output for the command. If the action is a search request, then the wearable computing device can: communicate the search request to a search engine, receive search results from the search engine, and generate output based on the search results. The output can be provided using output component(s) of the wearable computing device.