Semantic Map Generation for Smart Contract Interpretation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Smart contracts and self-executing protocols face challenges in interpretation and enforcement due to reliance on imprecise human interpretation systems, especially when contract terms are complex or evolve over time, leading to ambiguity and resource wastage.

Innovation Solution

A process and system for generating a semantic map from natural-language-text documents, using data model objects and machine learning to create a structured representation of contract terms, enabling systematic and unambiguous interpretation and enforcement across various domains.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If natural-language-text documents are used for smart contracts, then ease of operation is improved, but measurement precision deteriorates due to imprecise human interpretation

Engineering Contradiction:

Improveease of operationVSAvoidmeasurement precision

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent introduces an intermediary system consisting of data model objects, embedding sequences, and semantic maps that translate natural language clauses into structured representations. This intermediary layer preserves the ease of natural language operation while achieving machine-level precision through systematic interpretation rules and shared parameter matching.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical human interpretation system with an automated computational system that uses embedding sequences, data model objects, and algorithmic matching based on shared parameters. This substitution eliminates human subjectivity while maintaining natural language input, achieving both ease of operation and measurement precision.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If complex contract terms are interpreted using human systems, then adaptability is improved, but reliability deteriorates due to ambiguity

Engineering Contradiction:

ImproveadaptabilityVSAvoidreliability

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent segments complex contract terms into discrete data model objects with specific fields (n-grams, categories, parameters). Each segment is independently processed and associated through shared parameters, allowing the system to handle complex terms systematically while eliminating ambiguity through structured representation.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent transforms unstructured natural language into structured parameters through embedding sequences and data model objects. By converting contract terms into standardized parameters with defined categories and associations, the system achieves both adaptability to complex terms and reliability through consistent parameter-based interpretation.

Inventive Principle:

Principle #35Parameter changes

3Device complexity

If traditional interpretation systems are used, then device complexity is reduced, but loss of information increases due to ambiguous interpretation

Engineering Contradiction:

Improvedevice complexityVSAvoidloss of information

Core Design Contradiction:

Device complexityVSLoss of information

Solution Approach 1:

The patent performs preliminary action by pre-processing natural language clauses into embedding sequences and data model objects before interpretation. This preliminary structuring preserves all original information in a machine-readable format, preventing information loss while the modular architecture keeps overall system complexity manageable.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent uses a nested structure where natural language clauses contain n-grams, which are embedded in embedding sequences, which are then represented as data model objects with multiple fields. This nested organization preserves all information at each level while maintaining a manageable external interface, reducing apparent complexity while preventing information loss.

Inventive Principle:

Principle #7Nested doll (Nesting)

Data Source

PatentUS20240135106A1Semantic map generation from natural-language-text documents

Publication Date: 2024.04.25 DIGITAL ASSET CAPITAL INC

AI summary

A computer-implemented process includes obtaining a natural-language-text document comprising a first and second clause and determining first and second embedding sequences based on n-grams of the first and second clauses. The process includes generating data model objects based on the embedding sequences and determining an association between the first data model object and the second data model object based on a shared parameter of the first and second clauses. The process includes receiving a query including the first category and the first n-gram and causing a presentation of a visualization of data model objects that includes shapes based on the data model objects and a third shape based on the association between the first data model object and the second data model object.