Hybrid Electronic Invoice Data Processing Using Segmentation and Intermediary Parsing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies fail to accurately identify, process, and adjudicate hybrid electronic invoice data containing both pharmacy and non-pharmacy charges, leading to processing errors and inefficiencies.
Innovation Solution
An invoice management computing apparatus that uses parsing techniques to disassemble and adjudicate charge data based on specific procedures, employing machine learning to identify and transform hybrid electronic invoice data, ensuring accurate processing of pharmacy and non-pharmacy charges.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If hybrid electronic invoice data containing both pharmacy and non-pharmacy charges is processed using current automated technologies, then processing speed is improved, but processing accuracy deteriorates due to inability to accurately identify and adjudicate different charge types
Solution Approach 1:
The patent segments hybrid electronic invoice data into distinct pharmacy charge portions and non-pharmacy charge portions using parsing techniques. The system identifies specific data elements such as National Drug Codes (NDC) for pharmacy charges and separates them from other charge types, allowing each segment to be processed according to its specific adjudication requirements, thereby maintaining both speed and accuracy.
Solution Approach 2:
The patent introduces an intermediary processing layer that acts as a mediator between raw hybrid invoice data and final adjudication. This intermediary system uses machine learning models and parsing algorithms to identify, disassemble, and reassemble charge data portions, applying appropriate adjudication procedures to each type before consolidation, thus resolving the contradiction between automated speed and processing accuracy.
2Measurement precision
If parsing techniques are used to identify and disassemble charge data from hybrid electronic invoices, then processing accuracy is improved, but device complexity increases
Solution Approach 1:
The patent implements a universal parsing and identification system that handles multiple types of charge data (pharmacy, non-pharmacy, supplies, equipment) through a single integrated platform. The machine learning model is trained to recognize various data formats and charge types universally, reducing the need for separate processing systems for different charge types while maintaining high identification accuracy.
Solution Approach 2:
The patent changes the parameters of the processing system by implementing machine learning models that dynamically adjust identification criteria based on the specific characteristics of incoming invoice data. The system modifies parsing parameters such as data format expectations, charge code patterns, and adjudication rules based on the identified charge type, enabling accurate processing without requiring complex hard-coded rules for every scenario.
3Reliability
If different adjudication procedures are applied to different charge data types, then processing reliability is improved, but processing time increases
Solution Approach 1:
The patent applies preliminary action by pre-identifying and categorizing charge data portions during the parsing phase before adjudication begins. The system pre-assembles appropriate adjudication procedure sets based on the identified charge types (pharmacy, non-pharmacy, etc.), so that when adjudication occurs, the correct procedures are already ready to be applied, eliminating the need for time-consuming procedure selection during the adjudication process itself.
Solution Approach 2:
The patent maintains continuity of useful action by implementing a streamlined workflow where parsing, identification, disassembly, and adjudication occur in a continuous automated sequence without manual intervention. The system continuously processes incoming hybrid invoices through the pipeline, with each stage feeding seamlessly into the next, ensuring that the benefits of multiple adjudication procedures are realized without significant time loss.
Data Source
AI summary
Methods, non-transitory computer readable media, and apparatuses for automated processing of hybrid electronic invoice data include identifying at least a first type of charge data from one or more other types of charge data in received hybrid electronic invoice data based on one or more parsing techniques. The first type of charge data is disassembled from the received hybrid electronic invoice data based on the identification. The disassembled first type of charge data is adjudicated based on execution of one of a plurality of sets of adjudication procedures identified to correspond to the disassembled first type of charge data. The received hybrid electronic invoice data is transformed with the adjudicated first type of charge data. The transformed electronic invoice data is provided for additional processing.