Electronic Object for Natural Language to Machine Action Mapping

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing voice control systems are inflexible and narrowly tailored to specific devices and voice prompts, limiting user customization and adaptability.

Innovation Solution

A method and system that generate electronic objects using specification data to map natural language inputs to processor-generated outputs, allowing for the creation of customizable mappings between natural language commands and machine actions, including the use of recursive grammar rules.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional voice control systems are used, then the system is simple to implement, but the system is inflexible and narrowly tailored to specific devices

Engineering Contradiction:
ImproveadaptabilityVSAvoidcomplexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent creates a universal natural language processing system that can control multiple different devices and perform various functions through a single electronic object. The system uses a grammar-based approach that can be configured to work with different devices, making it multi-functional and adaptable rather than device-specific.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system dynamically generates machine actions from natural language input through configurable grammar rules. The electronic object can be adapted to different contexts and devices by modifying the grammar specifications, allowing the system to change its behavior and mappings based on requirements without reprogramming the entire system.

Inventive Principle:
Principle #15Dynamics

2Adaptability or versatility

If traditional voice control systems are used, then the system has fixed functionality, but user customization is limited

Engineering Contradiction:
ImprovecustomizationVSAvoidconfiguration complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system performs preliminary configuration by defining grammar specifications and mappings before actual natural language processing occurs. The electronic object is pre-configured with grammar rules that map natural language patterns to machine actions, allowing users to customize the system's behavior in advance rather than requiring complex runtime configuration.

Inventive Principle:
Principle #10Preliminary action

3Adaptability or versatility

If device-specific voice prompts are used, then the system is simple to implement, but the system cannot respond to different voice commands across devices

Engineering Contradiction:
Improvecross-device compatibilityVSAvoidsystem architecture
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary electronic object that acts as a mediator between natural language input and device-specific actions. This electronic object contains configurable grammar specifications that translate universal natural language commands into device-specific operations, enabling cross-device compatibility without requiring device-specific voice prompts for each device.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS10095691B2Method and apparatus for converting natural language to machine actions
Publication Date: 2018.10.09 WOLFRAM RESEARCH
  • US10095691B2 patent drawing
  • US10095691B2 patent drawing
  • US10095691B2 patent drawing

AI summary

First specification data defining a grammar corresponding to natural language, and second specification data defining a mapping between the grammar and one or more outputs to be generated, are received. An electronic object is generated using the first specification data and the second specification data, the electronic object being configured to, when executed by one or more processors, cause the one or more processors to map received natural language input to the one or more outputs. The one or more outputs may be used to control an electronically controllable machine.