ML-Based Billing Dispute Prioritization and Automation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current billing dispute management systems are cumbersome and labor-intensive, often resulting in arbitrary dispute resolutions due to manual investigation processes, which are inefficient and prone to errors.

Innovation Solution

A computer-implemented method and system that uses machine learning techniques to receive dispute information, compute a validity score, categorize disputes, and present actions to resolve them, thereby automating the dispute resolution process and prioritizing investigations based on the computed score.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual investigation processes are used to determine dispute validity, then detailed human review can be performed, but the process becomes labor-intensive and arbitrary

Engineering Contradiction:

Improvedispute validity determination accuracyVSAvoidinvestigation process complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces the manual mechanical investigation process with an automated machine learning system. The ML model computes a validity score based on dispute information and historical data, eliminating the need for manual document review and human agent investigation, thereby reducing labor intensity while maintaining determination accuracy

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service dispute resolution by automatically computing validity scores and categorizing disputes without human intervention. The automated classification system processes dispute information and determines validity independently, reducing reliance on manual investigation while improving consistency

Inventive Principle:

Principle #25Self-service

2Reliability

If all disputes are investigated manually, then thorough review is possible, but processing time and labor costs increase significantly

Engineering Contradiction:

Improvedispute resolution reliabilityVSAvoiddispute processing throughput

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system applies partial investigation by using automated ML scoring for all disputes while reserving manual investigation only for edge cases or high-value disputes. The validity score calculation processes dispute information automatically, achieving reliable results for the majority of cases without full manual review, thus improving throughput while maintaining reliability

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The patent segments disputes into different categories based on computed validity scores. High-confidence disputes (clearly valid or invalid) are resolved automatically, while ambiguous cases are flagged for manual review. This segmentation enables parallel processing of different dispute types, significantly improving overall processing throughput

Inventive Principle:

Principle #1Segmentation

3Productivity

If automated scoring is implemented, then processing efficiency improves, but the system complexity increases

Engineering Contradiction:

Improvedispute processing efficiencyVSAvoidsystem architecture complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The machine learning system serves multiple functions: it computes validity scores, categorizes disputes, prioritizes investigations, and provides recommendations. This multi-functional automated core replaces multiple separate manual processes, improving overall processing efficiency while the modular architecture manages system complexity through reusable components

Inventive Principle:

Principle #6Universality (Multi-functionality)

4Loss of information

If manual document review is performed, then comprehensive information analysis is achieved, but the investigation becomes cumbersome and time-consuming

Engineering Contradiction:

Improveinformation completenessVSAvoidinvestigation time

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The system replaces manual document review with automated information extraction and analysis using machine learning. The ML model processes dispute information, billing data, and historical records automatically, achieving comprehensive information analysis without manual document examination, thereby eliminating time loss while maintaining information completeness

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11514539B2Prioritization and automation of billing disputes investigation using machine learning

Publication Date: 2022.11.29 FLOWCAST INC

AI summary

The present disclosure provides a computer-implemented method, which includes receiving a dispute information pertaining to a billing dispute by a processor, from a device associated with a customer. The method includes computing, by the processor, a score based on the dispute information, for determining validity of the billing dispute. The billing dispute is categorized based on the score computed for the dispute information. One or more actions are subsequently presented to one or more parties associated with the dispute information for resolving the billing dispute. The processor is also configured to prioritize the one or more actions based on the score computed. The present disclosure also provides a system capable of implementing the aforesaid method for prioritizing and resolving the billing disputes in an automated manner.