Litigation Risk Prediction Using ML and NLP in Construction Correspondence

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current systems lack a computer-intelligent method to identify early signs of potential disputes and litigation risks in construction and engineering projects from electronic correspondences, which are costly and impactful if not addressed proactively.

Innovation Solution

A machine learning-based monitoring system that uses semantic natural language understanding to analyze electronic communications in real-time, predicting litigation risks and providing alerts, and incorporates user feedback to improve prediction accuracy over time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual analysis of electronic correspondences is used to identify litigation risks, then measurement precision can be maintained through human expertise, but productivity is severely limited by the time-consuming nature of manual review

Engineering Contradiction:

Improvevolume of correspondence analyzedVSAvoidaccuracy of risk identification

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent replaces manual human analysis (mechanical system) with an automated machine learning system that uses natural language processing to analyze electronic correspondences. The system processes text data through trained models to identify litigation risks automatically, eliminating the need for manual review while maintaining or improving accuracy through consistent application of learned patterns across large volumes of correspondence.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If comprehensive analysis of all correspondence text is performed to improve detection accuracy, then measurement precision improves, but loss of time increases due to processing volume

Engineering Contradiction:

Improvedetection accuracy of litigation risksVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies preliminary action by pre-training machine learning models on historical correspondence data labeled with litigation outcomes before deployment. This pre-processing phase allows the system to learn patterns and features associated with litigation risks in advance, enabling rapid real-time analysis of new correspondence without requiring comprehensive manual review, thus reducing processing time while maintaining detection accuracy.

Inventive Principle:

Principle #10Preliminary action

3Measurement precision

If a sophisticated machine learning model is deployed to improve detection accuracy, then measurement precision improves, but device complexity increases

Engineering Contradiction:

Improvelitigation risk prediction accuracyVSAvoidsystem architecture complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the machine learning system into distinct functional modules: text preprocessing module, feature extraction module, classification model module, and output generation module. Each module performs a specific function in the analysis pipeline, making the overall complex system more manageable and maintainable while achieving high detection accuracy through specialized processing at each stage.

Inventive Principle:

Principle #1Segmentation

4Loss of time

If real-time analysis of electronic correspondence is implemented to enable proactive interventions, then loss of time in dispute resolution is reduced, but use of energy and computational resources increases

Engineering Contradiction:

Improvetime to identify litigation risksVSAvoidcomputational resource consumption

Core Design Contradiction:

Loss of timeVSUse of energy by moving object

Solution Approach 1:

The patent implements periodic action by analyzing correspondence at strategically determined intervals rather than continuously processing every message in real-time. The system can analyze correspondence daily, weekly, or based on triggered events such as keywords or sender patterns, enabling timely identification of litigation risks while significantly reducing computational resource consumption compared to continuous real-time analysis.

Inventive Principle:

Principle #19Periodic action

Data Source

PatentUS11615361B2Machine learning model for predicting litigation risk in correspondence and identifying severity levels

Publication Date: 2023.03.28 ORACLE INT CORP

AI summary

Systems, methods, and other embodiments associated with detecting severity levels of risk in an electronic correspondence are described. In one embodiment, a method includes inputting, into a memory, a target electronic correspondence that has been classified as being litigious by a machine learning classifier. An artificial intelligence rule-based technique is applied to the target electronic correspondence that identifies high and medium risk level keywords. The technique is also configured to generate a litigious score based on a sum of term frequencies-inverse document frequencies using the remaining keywords. An electronic notice is transmitted to a remote computer over a communication network that identifies the target electronic correspondence and the level of litigation risk.