Context-Aware Declarative Knowledge Storage for Natural Language Understanding

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current technologies face challenges in effectively modeling human thought and understanding natural language, as they struggle with interpreting the intended meaning behind utterances, requiring breakthroughs in Knowledge Representation, Natural Language Theory, and Language Understanding Software, and lack a satisfactory theory of how grammatical function and punctuation work in natural language processing.

Innovation Solution

A system and method for storing declarative knowledge in a computer database that mimics the complexity of human thought, using a database structure and parser module to process natural language inputs, identifying context, and performing searches to retrieve appropriate responses, with a focus on closed-domain knowledge and pre-encoded vocabulary, allowing for precise storage and processing of complex language expressions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If traditional knowledge representation schemes (RDF, OWL, Cyc) are used to model human thought, then structured data storage is achieved, but the ability to capture intended meaning and contextual nuance deteriorates

Engineering Contradiction:

Improveloss of intended meaningVSAvoidcomplexity of knowledge representation

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The patent segments natural language expressions into discrete linguistic units (words, phrases, sentences) and maps them to corresponding database rows. Each linguistic unit is processed independently through parsing and context identification, allowing the system to handle complex meaning by breaking it down into manageable segments that can be stored and retrieved separately while preserving their semantic relationships.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary layer of context compartments and parser modules that bridge natural language expressions and database storage. This intermediary structure translates human language into a format suitable for computer storage while preserving the intended meaning through context-aware processing, rather than directly mapping raw data structures to semantic content.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Adaptability or versatility

If comprehensive natural language processing is implemented to understand human thought, then language understanding capability is improved, but processing time and computational resources increase

Engineering Contradiction:

Improvenatural language understanding capabilityVSAvoidprocessing time

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent performs preliminary parsing and context identification on natural language expressions before full database searching. By pre-processing the input to identify key context compartments and relevant database sections, the system reduces the scope of subsequent searches, thereby maintaining high natural language understanding capability while minimizing actual processing time during query execution.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements partial searching by focusing only on relevant context compartments identified through parsing, rather than searching the entire database. This selective approach applies excessive action only where needed (in depth analysis of relevant sections) while using minimal action for unrelated areas, optimizing the balance between understanding capability and processing efficiency.

Inventive Principle:

Principle #16Partial or excessive action

3Measurement precision

If detailed context compartments are created to represent nuanced human thought, then precision of meaning representation is improved, but database structure complexity increases

Engineering Contradiction:

Improveprecision of meaning representationVSAvoiddatabase structure complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent adds a contextual dimension to database organization by creating context compartments that layer semantic information over the base data structure. Rather than flattening all relationships into a single complex schema, the system uses multi-dimensional context layers that can be navigated and queried independently, achieving precise meaning representation while maintaining manageable structural complexity through dimensional separation.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS9805020B2In-context access of stored declarative knowledge using natural language expression

Publication Date: 2017.10.31 THE GORMAN FAMILY TRUST

AI summary

Identifying a context for parsing a natural language expression. In an embodiment, a table comprising rows addressed according to context compartments is disclosed. Each compartment represents a context and comprises row(s), and each row represents a concept and comprises an outline field indicating an order of the concept in its context. Input expression(s) are received, and a first search is performed on the table to identify rows representing concepts corresponding to element(s) of the expression(s) and rows representing concepts corresponding to combinations of concepts represented by previously identified rows until a first row representing a higher-order concept is identified. Based on the first row, a first context compartment is determined, and a second search, that is restricted to the first context compartment, is performed to identify a second row representing a concept corresponding to an entirety of at least one of the input expression(s).