Financial Data Parsing with XBRL Tagging and Contextual Hyperlinks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for extracting financial data from documents are cumbersome and prone to errors, lacking the ability to efficiently view associated information like footnotes in context, which is crucial for comprehensive financial analysis.
Innovation Solution
A system and method for parsing and categorizing associated information in financial documents, using XBRL standards to tag and filter data, allowing users to view relevant footnotes and metadata in context within a spreadsheet environment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual copy and paste method is used to transfer financial data from documents to spreadsheets, then data can be transferred, but the process is cumbersome and time consuming and prone to errors
Solution Approach 1:
The patent replaces the manual mechanical copy-paste process with an automated computer-based system that uses optical character recognition (OCR) and intelligent parsing algorithms to extract financial data directly from documents and populate spreadsheets, eliminating manual intervention and its associated errors
Solution Approach 2:
The system enables self-service data extraction where the software automatically identifies financial statement structures, extracts relevant data, and populates spreadsheets without requiring user intervention, making the process both faster and more reliable
2Ease of operation
If financial data is extracted and normalized into spreadsheets for analysis, then data manipulation capability is improved, but the ability to view associated information like footnotes in context is lost
Solution Approach 1:
The patent implements a nested structure where the spreadsheet contains embedded hyperlinks that point back to the original document sections, footnotes, and associated information, allowing users to navigate from the extracted data back to its source context without leaving the spreadsheet environment
Solution Approach 2:
The system introduces hyperlinks as an intermediary element that connects the extracted financial data in the spreadsheet to the original associated information in the source document, enabling context retrieval without manual searching
3Measurement precision
If XBRL tagging is implemented to describe financial data meaning, then data identification accuracy is improved, but the complexity of the system increases
Solution Approach 1:
The patent applies XBRL tagging and metadata assignment during the initial data extraction phase rather than requiring separate post-processing steps, preliminarily structuring the data with proper identifiers and descriptions that enable accurate identification throughout subsequent analysis
Solution Approach 2:
The system uses universal XBRL tags and metadata standards that can identify and describe multiple types of financial data elements across different document formats and structures, providing a single framework that handles diverse financial information without requiring separate custom solutions
Data Source
AI summary
A method of viewing information associated with data in a spreadsheet, includes providing a document including data and information associated with the data, parsing the document to retrieve the associated information, processing the associated information to break the associated information down into at least one sentence, categorizing the at least one sentence to determine whether the at least one sentence corresponds to at least one category in a taxonomy corresponding to the data, assigning an association strength to the categorized at least one sentence, the association strength indicating a likelihood that the categorized at least one sentence actually corresponds to the at least one category in the taxonomy, filtering the at least one categorized sentence based on the association strength to determine whether to match the categorized at least one sentence with the at least one category in the taxonomy and outputting only the categorized at least one sentence matched with the at least one category in the taxonomy.


