Voice Command Parsing for Complex Natural Language Inputs

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional voice and text-based interfaces are limited to simple commands and struggle to process complex, natural language inputs, failing to provide intuitive and natural responses to users.

Innovation Solution

A system that processes complex inputs by separating them into discrete actions using natural language processing, employing a rule set to match inputs and recombine outputs for concise and natural responses, supporting both voice-based and text-based inputs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional voice and text-based interfaces are used for simple commands, then the system operation is simple and reliable, but the interface cannot process complex natural language inputs and lacks intuitiveness

Engineering Contradiction:
Improvecapability to process complex natural language inputsVSAvoidsystem processing complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent applies segmentation by dividing complex natural language inputs into discrete actionable components. The system breaks down compound inputs into separate actions, objects, and parameters that can be individually processed and executed, enabling the interface to handle complex commands while maintaining manageable system complexity through modular processing.

Inventive Principle:
Principle #1Segmentation

2Ease of operation

If complex commands are processed by separating into discrete actions using natural language processing, then the user interface becomes more intuitive and natural, but the processing complexity and computational requirements increase

Engineering Contradiction:
Improveuser interface intuitivenessVSAvoidprocessing complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The system applies self-service by automatically analyzing and structuring natural language inputs without requiring user intervention. The natural language processing engine autonomously parses commands, identifies actions and objects, and formulates execution plans, making the interface intuitive while managing processing complexity through automated linguistic analysis rather than manual command structuring.

Inventive Principle:
Principle #25Self-service

3Measurement precision

If explicit punctuation and word separation are required for command processing, then the system can accurately parse inputs, but the user experience becomes less natural and more cumbersome

Engineering Contradiction:
Improveinput parsing accuracyVSAvoiduser interaction naturalness
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces the mechanical system of requiring explicit punctuation and word separation with a natural language processing system that uses linguistic analysis. Instead of relying on structural delimiters, the system employs semantic understanding, context analysis, and pattern recognition to accurately parse inputs, achieving both high parsing accuracy and natural user interaction by substituting mechanical parsing rules with intelligent linguistic processing.

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

Data Source

PatentUS10714087B2Speech control for complex commands
Publication Date: 2020.07.14 JOSH AI INC
  • US10714087B2 patent drawing
  • US10714087B2 patent drawing
  • US10714087B2 patent drawing

AI summary

Audio content associated with a verbal utterance is received. An operational meaning of a received verbal utterance comprising a compound input is recognized and determined, at least in part by: determining that a first subset of the received verbal utterance is associated with a first recognized input; determining whether a meaning of a remaining portion of the received verbal utterance other than the first subset is recognized as being associated with a second recognized input; and based at least in part on a determination that the meaning of the remaining portion of the received verbal utterance is recognized as being associated with said second recognized input, concluding that the verbal utterance comprises a compound input comprising the first and second recognized inputs.