Natural Language Command Routing via Context-Specific Skill Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current natural language processing systems lack the ability to tailor actions performed in response to natural language inputs across different devices and users, resulting in inconsistent user experiences and inappropriate responses based on device context and user preferences.

Innovation Solution

The system employs context data to differentiate actions by identifying device and user contexts, allowing for the invocation of specific skill components associated with device manufacturers, business entities, and users, ensuring that actions are tailored to the device and user context, such as location and ownership, thereby providing customized responses.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a single generic skill component is used for all devices and users, then system complexity is reduced, but user experience consistency and context-appropriateness deteriorate

Engineering Contradiction:
Improvecontext-specific response capabilityVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The skill component system is segmented into multiple distinct skill components, each associated with specific device manufacturers, business entities, or users. This segmentation enables context-specific responses while maintaining manageable organization through the orchestrator that selects appropriate components based on input metadata.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Different skill components are assigned to different device manufacturers, business entities, or users based on local context requirements. Each skill component is optimized for its specific target audience or device type, providing localized quality and relevance rather than a one-size-fits-all approach.

Inventive Principle:
Principle #3Local quality

2Reliability

If context data is collected and processed to differentiate actions, then user experience consistency improves, but data processing complexity and privacy concerns worsen

Engineering Contradiction:
Improveinteraction accuracyVSAvoiddata processing complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

Context data is collected and processed in advance before the actual skill component execution. The orchestrator pre-determines which skill component should be invoked based on device metadata, user identity, and business entity associations, reducing real-time processing complexity while maintaining high interaction accuracy.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The orchestrator acts as an intermediary between the natural language input and the skill component execution. It processes context data, selects appropriate skill components, and coordinates their execution, thereby managing data processing complexity centrally while improving overall system reliability.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Adaptability or versatility

If skill components are tailored to specific device manufacturers and business entities, then response appropriateness improves, but system flexibility and cross-platform capability worsen

Engineering Contradiction:
Improvecontext-specific response capabilityVSAvoidsystem response efficiency
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The orchestrator provides universal functionality across different device manufacturers, business entities, and users. It manages multiple skill components with specific tailoring while maintaining a unified interface and processing workflow, enabling efficient cross-platform operation without sacrificing context-specific responsiveness.

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

Solution Approach 2:

The system dynamically selects and invokes appropriate skill components based on the input context, including device manufacturer, business entity, and user identity. This dynamic adaptation allows the system to maintain high efficiency while providing tailored responses to different contexts.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS11145295B1Natural language command routing
Publication Date: 2021.10.12 AMAZON TECH INC
  • US11145295B1 patent drawing
  • US11145295B1 patent drawing
  • US11145295B1 patent drawing

AI summary

Techniques for improving routing of natural language inputs, of a natural language processing (NLP) system, are described. A natural language input may be routed based on the device that captured the natural language input. A device manufacturer, hospitality provider, business, etc. may cause the NLP system to generate a skill component specific to the device manufacturer, hospitality provider, business, etc. Thereafter, when a natural language input is received from the device, the NLP system may route the natural language input to the device manufacturer-, hospitality provider-, business-, etc.-specific skill component for processing.