Financial Text to Code Conversion via Partial Parsing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Financial management programs, such as tax preparation software, require manual review and translation of numerous financial documents into computer-readable code, which is inefficient due to frequent updates and varying document formats, leading to a need for an automated system to convert natural language text to mathematical operations.

Innovation Solution

A method and system that utilize a computing device to parse and translate segments of text from financial documents into computer-readable mathematical operations by tokenizing, lemmatizing, and associating n-grams with operators and variables, allowing for partial parsing and recursive translation to generate executable code without requiring complete parsing of the entire document.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual review and translation of financial documents is performed, then accuracy of code translation is maintained, but productivity is reduced due to the time-consuming nature of manual processing

Engineering Contradiction:

Improveaccuracy of code translationVSAvoidprocessing speed

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent introduces an automated natural language processing system as an intermediary between financial documents and computer-readable code. This intermediary uses parsing algorithms, translation rules, and data structures to automatically convert document text into executable operations, eliminating the need for manual translation while maintaining accuracy through structured processing methods

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical manual process of reviewing and translating financial documents with an automated computational system. The system uses computer algorithms to parse text, identify operations, and generate code automatically, substituting human manual labor with machine-based processing that is both faster and consistently accurate

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If complete parsing of entire document segments is performed, then translation accuracy is ensured, but processing time increases significantly

Engineering Contradiction:

Improvetranslation accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent divides financial document text into smaller manageable segments or chunks rather than processing entire documents at once. Each segment is parsed and translated independently, allowing the system to process only relevant portions of text while maintaining translation accuracy through focused analysis of discrete units

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent implements partial parsing where the system processes only the portion of text necessary to extract meaningful operations rather than completely parsing entire document segments. The system identifies and processes relevant n-grams and translates them while skipping unnecessary text, achieving sufficient translation accuracy without the time cost of complete parsing

Inventive Principle:

Principle #16Partial or excessive action

3Productivity

If automated text conversion system is implemented, then productivity is improved through faster processing, but device complexity increases due to multiple processing components

Engineering Contradiction:

Improvedocument processing speedVSAvoidsystem architecture complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent designs a unified processing system where core components serve multiple functions. The parsing module handles both text segmentation and operation identification, the translation engine performs both syntax conversion and semantic mapping, and the same data structures support both processing and output generation, reducing overall system complexity through multi-functional design

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS11783128B2Financial document text conversion to computer readable operations

Publication Date: 2023.10.10 INTUIT INC

AI summary

This disclosure provides systems, methods and apparatuses for converting natural language text in financial documents to mathematical operations for a financial management program. In some implementations, a computing device may obtain a first segment of computer readable text associated with a text capture in a financial document, parse only a portion of the first segment to generate a parsed segment, and determine translation information associated with the parsed segment to translate the parsed segment. The computing device may also store the parsed segment and the translation information in a data structure in memory, translate the parsed segment in the data structure based on the translation information, and output one or more computer readable mathematical operations corresponding to the translated segment. In this manner, the computing device may output the one or more computer readable mathematical operations without parsing all of the segment.