Method and system for enhanced LLM analysis with application to accounting data

The AI-powered preprocessing of PDF financial data into structured transaction data addresses inefficiencies in traditional methods, achieving rapid, accurate, and cost-effective financial analysis by creating a coherent database for multiple accounting models.

WO2025244864A2PCT designated stage Publication Date: 2025-11-27DYE DANAMICHELE BRENNEN
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
PCT/US2025/028706
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2024-05-09
Filing Date
2025-05-09
Publication Date
2025-11-27

AI Technical Summary

Technical Problem

Traditional methods for extracting and processing financial data from PDF statements are inefficient, inaccurate, and require manual intervention, struggling with diverse statement formats and failing to reconcile data with beginning and ending balances, leading to incomplete and error-prone financial analysis.

Method used

A computer utility using AI large language models (LLMs) to preprocess PDF financial data, converting it into structured transaction data with enhanced vendor information, and reconciling it to create a coherent database for direct import into accounting systems, allowing multiple accounting models to be applied to the same data.

Benefits of technology

This approach significantly reduces encoding, categorization, and reconciliation times, enhances data accuracy, and eliminates manual intervention, enabling efficient and flexible financial analysis with cost savings and improved data integrity.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure IMGF000007_0001
    Figure IMGF000007_0001
  • Figure IMGF000010_0001
    Figure IMGF000010_0001
  • Figure IMGF000010_0002
    Figure IMGF000010_0002
Patent Text Reader

Abstract

A method and system for enhanced financial data processing using large language models (LLMs) to transform PDF statements into structured accounting data. The invention preprocesses statements with line numbering, character position tagging, and data partitioning to overcome LLM context limitations. The system extracts transactions, reconciles them with statement balances, normalizes vendor information, and generates enhanced output files compatible with standard accounting platforms. This enhanced transaction data collapses reconciliation and categorization times in downstream accounting systems. The system creates a robust vendor-transaction database supporting direct analysis or simultaneous application of multiple accounting models.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Cited By

  • Machine account checking method and system based on AI large model, electronic equipment and medium

    CN121788283A