Contract Object Model for Machine Evaluation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in efficiently translating contractual terms from word-based documents into machine-readable data, managing the complexity of contract changes over time, and comparing contracts across diverse industries and scenarios.
Innovation Solution
The development of a multi-tier contract object model that breaks contracts into three object types – contract objects, transaction objects, and document objects – allowing for the evaluation and tracking of contract terms over their lifetime, and the use of machine learning algorithms to classify and analyze contractual data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If contracts are expressed as words with variable wording and formatting for human consumption, then readability and human understanding are improved, but machine processing capability deteriorates
Solution Approach 1:
The patent introduces an intermediary layer between human-readable contract text and machine processing. This intermediary is a structured data model with standardized fields (e.g., party names, dates, obligations) that acts as a mediator, allowing contracts to maintain their natural language format for humans while providing structured data for machines to process automatically
Solution Approach 2:
The patent replaces manual mechanical text analysis with automated natural language processing (NLP) and machine learning algorithms. These systems automatically extract, classify, and structure contract terms without human intervention, transforming unstructured text into organized data that machines can efficiently process
2Measurement precision
If manual extraction of contract data by human experts is used, then data accuracy is improved, but cost and time consumption increase
Solution Approach 1:
The patent implements self-service automation where the system automatically extracts, validates, and structures contract data without requiring human expert intervention for each contract. The machine learning models continuously learn from extracted data, improving accuracy over time while maintaining high throughput and low cost
Solution Approach 2:
The patent incorporates feedback mechanisms where extracted contract data is validated against business rules and historical patterns. Discrepancies are flagged for review, and the system continuously learns from corrections made by users, improving extraction accuracy while maintaining automated processing efficiency
3Device complexity
If contracts are tracked as individual documents without time dimension, then simplicity is improved, but ability to track prevailing terms deteriorates
Solution Approach 1:
The patent adds a temporal dimension to contract tracking by implementing version control and effective date tracking. Each contract term is associated with time stamps and version identifiers, allowing the system to track how terms evolve over time through amendments and renewals while maintaining a clear view of prevailing terms at any given moment
Solution Approach 2:
The patent segments contracts into discrete, trackable components such as individual clauses, obligations, and parties. Each segment can be independently versioned and tracked through changes over time, allowing precise monitoring of prevailing terms without requiring complex full-document version control
4Adaptability or versatility
If diverse contract types and industry-specific jargon are used, then adaptability to different industries is improved, but comparability across enterprise portfolio deteriorates
Solution Approach 1:
The patent implements a universal contract data model that can represent diverse contract types and industry-specific terms through a common structure. The system uses standardized field names and data types that work across all contract types, while allowing custom extensions for industry-specific requirements, enabling both adaptability and comparability simultaneously
Data Source
AI summary
Embodiments of the present disclosure provide a method that may include defining an object model containing a structural representation of events and artifacts through which contracts are created, changed, and brought to an end. The method may include accessing a machine learning classifier comprising a plurality of rule sets. The method may include applying the plurality of rule sets to one or more words of each corresponding contract document. The method may include linking identified one or more core attributes and one or more words of each corresponding contract document to an applicable object of the object model, determining prevailing terms of each corresponding contract document, and evaluating contract data variables and assigning a contract data risk value to one or more of contract data values. The method may include communicating an alert via email or text message when a contract risk exceeds a threshold value.