LLM-Powered Transaction Dispute Resolution From Digital Documents
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional systems face inefficiencies and inaccuracies in processing transaction disputes for electronic payment transactions, lacking the ability to quickly and accurately access digital documentation, leading to compliance issues and delayed dispute resolutions.
Innovation Solution
A machine-learning dispute system that utilizes digital content analysis tools to extract data from digital documents, generates model prompts for a large language model, and determines dispute resolution operations, such as approval or denial, based on the extracted data, thereby improving efficiency and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional systems process transaction disputes manually, then compliance with digital data requirements can be maintained, but processing speed and accuracy deteriorate
Solution Approach 1:
The patent replaces manual mechanical processing of dispute documentation with an automated machine learning system that uses optical character recognition (OCR) and natural language processing to extract and analyze data from digital documents, thereby maintaining compliance accuracy while dramatically improving processing speed
Solution Approach 2:
The patent introduces an intermediary machine learning model that acts as a mediator between the raw digital documentation and the dispute resolution decision, automatically extracting relevant information and redacting sensitive data to ensure both speed and compliance
2Loss of information
If conventional systems download and extract information from digital documentation, then dispute details can be accessed, but processing time increases and accuracy decreases
Solution Approach 1:
The patent applies preliminary action by pre-training machine learning models on vast amounts of transaction and dispute data before actual dispute resolution occurs. This pre-training enables the system to quickly and accurately extract relevant information from new documentation without time-consuming manual analysis
Solution Approach 2:
The patent uses copying by creating digital representations of physical or scanned documentation through OCR technology, then processing these copies through machine learning models to extract information rapidly without handling or manually reading the original documents
3Productivity
If automated systems resolve disputes quickly, then downstream operations benefit from timely resolutions, but compliance with digital data requirements may deteriorate
Solution Approach 1:
The patent implements feedback mechanisms where the machine learning system continuously monitors its own processing accuracy and compliance performance, adjusting its parameters and redaction rules based on feedback from compliance audits and resolution outcomes to maintain both speed and reliability
Data Source
AI summary
This disclosure describes methods, non-transitory computer readable storage media, and systems that use intelligent digital content analysis and large language models to resolve transaction disputes. The disclosed system selects appropriate digital content analysis tools for analyzing digital documentation including details of a transaction in response to a transaction dispute. The disclosed system utilizes data extracted from the digital documentation to generate a number and type(s) of model prompts to provide to a large language model based on attributes of the transaction dispute. The disclosed system uses responses generated by the large language model for the model prompts to determine a dispute resolution operation (e.g., approval, denial, or agent review). Furthermore, the disclosed system provides a response to the request to one or more computing devices associated with the request in response to execution of the dispute resolution operation.