Implicit Information Extraction via Logical Proposition Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current Natural Language Processing technologies fail to accurately extract implicit information from text, which hinders search engines in finding relevant information efficiently and limits the ability of artificial systems to make independent decisions based on written data.

Innovation Solution

A computer-executable program employing inductive and deductive reasoning to identify implicit information in sentences by analyzing morphological, syntactical, and semantic components, allowing it to infer information not explicitly stated or present in synonyms, enabling logical inferences and decision-making.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If statistical analysis or concordance based analysis is used to process natural language text, then the processing speed is fast, but the ability to detect implicit information is poor

Engineering Contradiction:
Improvedetection accuracy of implicit informationVSAvoidcomplexity of reasoning system
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system segments natural language text into individual sentences and further into atomic propositions that can be independently analyzed. This segmentation allows the reasoning engine to process complex text by breaking it down into manageable logical units, enabling accurate detection of implicit information while maintaining systematic control over the complexity of the reasoning process.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary layer of logical representation between the raw text and the implicit information detection. By translating natural language sentences into formal logical propositions with explicit subject-predicate-object structures, the system creates an intermediate representation that makes implicit relationships detectable through logical inference rules, bridging the gap between surface-level text and deeper meaning.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If deductive reasoning is implemented to find implicit information in text, then the accuracy of information extraction improves, but the processing time increases

Engineering Contradiction:
Improveaccuracy of implicit information extractionVSAvoidprocessing time for text analysis
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-processing text into standardized logical propositions before the main reasoning process. Sentences are parsed and converted into structured logical forms with identified subjects, predicates, and objects in advance, which prepares the data for faster deductive inference. This preliminary structuring reduces the computational burden during the actual implicit information detection phase.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent replaces traditional mechanical text search and pattern matching with logical deduction mechanisms. Instead of relying on keyword frequency or surface-level pattern recognition, the system uses formal logical inference rules to derive implicit information, substituting brute-force computational methods with more efficient logical reasoning that can leap directly to meaningful conclusions.

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

3Measurement precision

If the system analyzes up to five words in sequence to understand sentence meaning, then the understanding accuracy improves, but the computational complexity increases

Engineering Contradiction:
Improvesentence understanding accuracyVSAvoidcomplexity of word sequence analysis
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system segments the analysis process into fixed-size windows of up to five consecutive words, analyzing each local sequence independently to build overall sentence understanding. This segmentation approach manages computational complexity by limiting the scope of each analysis step while maintaining accuracy through systematic coverage of the entire text through overlapping or sequential windows.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS8560305B1logifolg
Publication Date: 2013.10.15 GEORGIEV HRISTO

AI summary

LOGIFOLG is a system and method for finding implicit information that is not explicitly mentioned in the sentence, not contained in the synonyms of the particular word, not present in the concept the word belongs to, not found with statistical or concordance based analysis. Nevertheless, this implicit information is present and understood, implicitly, consciously or unconsciously, by everybody who reads the text. LOGIFOLG uses a computer software process, such as computer-executable program code, to discover this implicit information. The steps in this process are: analyzing user's written input, up to five successive and non-successive words in a sequence, understanding the meaning of the written input, finding implicit information in the written input and finally, displaying the implicit information as a variant of the original sentence. The subject matter of the invention deals with Artificial Reasoning, namely inductive and deductive reasoning, based on Natural Language written sentences. The medium is non-transitory.