Image Transaction Processing Using Confidence-Based Document Splitting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing transaction processing systems struggle with handling varied sets of transactions without prior knowledge of the context, leading to inefficiencies and potential errors due to the need for manual processing and document pre-analysis.
Innovation Solution
A system utilizing an image processing engine with machine learning models to analyze document images, identify attributes, determine transactions, and associate them with accounts, based on confidence scores to split documents into sets, enabling automated and efficient transaction processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If manual transaction processing is used to handle varied transactions without prior knowledge, then flexibility in handling different transaction types is improved, but processing efficiency and accuracy deteriorate due to time-consuming manual analysis
Solution Approach 1:
The system performs self-service by automatically analyzing document images, extracting attributes, and determining transactions without requiring manual pre-analysis or prior knowledge of transaction contexts. The image processing engine independently handles the complete workflow from document intake to transaction determination, eliminating the need for manual intervention while maintaining adaptability to varied transaction types.
2Reliability
If document pre-analysis is required to process transactions, then transaction processing accuracy is improved, but system complexity and processing time increase
Solution Approach 1:
The system merges multiple functions into a single integrated image processing engine that simultaneously performs document analysis, attribute extraction, account identification, and transaction determination. This consolidation eliminates the need for separate pre-analysis steps while maintaining high accuracy through confidence score evaluation and automated processing workflows.
3Reliability
If manual review processes are used to verify transaction details, then error detection capability is improved, but processing speed and automation level deteriorate
Solution Approach 1:
The system implements feedback mechanisms through confidence score evaluation, where the image processing engine assesses the reliability of extracted attributes and automatically determines transactions based on predefined thresholds. This automated feedback loop provides error detection capability equivalent to manual review while maintaining high automation levels and processing speed.
Data Source
AI summary
Systems and methods, and computer readable media for image transaction processing are disclosed. The method receives an input of images of documents. The method may then analyze the input using an image processing engine to determine attributes associated with the images of the documents and identify an account linked to the attributes and a transaction associated with the account. The method may also evaluate confidence level of association links between the transaction and the account based on confidence scores of the attributes that may identify a type of the attribute.The method may use the transaction and account to split the images of documents into sets of images of documents with each set of images with confidence level of an association link between the transaction and the account associated with them being greater than a threshold value.