Natural Language Parsing for Combined Query and Command Processing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current speech recognition systems struggle to process natural language inputs that combine queries and communication commands, as they require careful definition and training, and cannot handle compound thoughts or ideas that depend on context.

Innovation Solution

A method that parses natural language inputs to separate query and communication portions, determines answers, and transmits them to the appropriate destinations, either locally or through a remote source, using communication channels and parameters identified from the input.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If conventional speech recognition systems are used to process natural language inputs, then the system can accept vocal commands, but the commands must be carefully defined and training is required for consistent recognition

Engineering Contradiction:
Improveease of useVSAvoidsystem complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The system segments the natural language input into distinct components: query portion and communication portion. This segmentation allows the system to process each component separately using appropriate methods, avoiding the need for comprehensive training on all possible command variations while maintaining ease of use.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system introduces an intermediary parsing layer that translates natural language into structured components before processing. This intermediary step bridges the gap between casual user speech and rigid system requirements, enabling easy operation without requiring complex training protocols.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If conventional speech recognition systems are used, then the system can recognize defined commands, but it cannot handle compound thoughts or ideas that depend on context

Engineering Contradiction:
Improvelanguage processing capabilityVSAvoidprocessing complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

By dividing the input into query and communication portions, the system can handle compound thoughts by processing the query aspect and the communication aspect separately, then integrating the results. This approach increases adaptability to complex language structures without proportionally increasing processing complexity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system dynamically determines whether to process queries locally or remotely based on the specific input requirements. This dynamic approach allows the system to adapt to different language complexities in real-time, handling simple queries efficiently and complex contextual queries by opening communication channels to remote sources as needed.

Inventive Principle:
Principle #15Dynamics

3Adaptability or versatility

If the system processes combined query and communication commands, then true natural language control is achieved, but the system must parse and separate query and communication portions

Engineering Contradiction:
Improvenatural language controlVSAvoidparsing complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The parsing process segments the natural language input into query portion and communication portion, enabling the system to achieve true natural language control by handling each segment with appropriate processing logic. This segmentation manages parsing complexity through systematic decomposition of the processing task.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS9507849B2Method for combining a query and a communication command in a natural language computer system
Publication Date: 2016.11.29 SOUNDHOUND AI IP LLC
  • US9507849B2 patent drawing
  • US9507849B2 patent drawing
  • US9507849B2 patent drawing

AI summary

A method for processing a natural language input to a computerized system. The method parses the input to identify a query portion and a communication portion of the input. The system then determines an answer to the query portion, including identifying communication parameters from the communication portion. Upon determining the answer, the system prepares an answer to the communication and transmits that answer. If the answer requires information from a remote source, the system creates a subsidiary query to obtain that information and then submits the subsidiary query to the remote source. A response to the query is used to compose the answer to the query from the answer to the subsidiary query. If the system concludes that the query portion does not require information from a remote source, analyzing and answering the query locally.