Automated Document Filing Using Machine Learning Nodes

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Managing electronic document databases is tedious and inefficient due to the difficulty in identifying appropriate filing locations for documents with generic or non-descriptive names, and the challenge of separating multiple documents within a single file.

Innovation Solution

A method and system for automatic ingestion and filing of documents in a database, using machine learning nodes to identify text data, generate suggested file locations, and separate distinct documents within a file, by processing text data at both a master node and a client node to refine suggestions based on keyword scores and location-specific weightings.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual document filing is performed, then document organization is achieved, but time consumption and labor effort increase significantly

Engineering Contradiction:

Improvedocument filing easeVSAvoidtime for document management

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system enables documents to automatically identify and file themselves into appropriate folders by extracting text content, generating keywords, and matching them with predefined folder structures without requiring manual user intervention for each document

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the manual mechanical process of document filing with an automated computer-based system that uses optical character recognition, text processing, and algorithmic matching to perform filing operations

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If documents are scanned as a batch into a single electronic file, then scanning efficiency improves, but document separation and filing complexity increases

Engineering Contradiction:

Improvescanning efficiencyVSAvoiddocument separation complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system automatically segments multi-document files by detecting page markers, analyzing text content boundaries, and separating individual documents within a single scanned file, then files each document to its appropriate location independently

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary text extraction and keyword generation on all documents within a batch file before separation, enabling efficient identification and classification of each document's destination folder

Inventive Principle:

Principle #10Preliminary action

3Ease of manufacture

If generic file names are used, then file creation is simplified, but file location identification becomes difficult

Engineering Contradiction:

Improvefile creation easeVSAvoidfile location identification difficulty

Core Design Contradiction:

Ease of manufactureVSDifficulty of detecting and measuring

Solution Approach 1:

The system performs preliminary text extraction and keyword generation from document content before filing, creating a searchable index that enables automatic matching with folder names and descriptions to identify appropriate filing locations

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces keywords as an intermediary between generic file names and specific filing locations, where extracted keywords serve as the matching mechanism to connect documents with their appropriate destinations without requiring descriptive file names

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11775866B2Automated document filing and processing methods and systems

Publication Date: 2023.10.03 FUTUREVAULT INC

AI summary

Systems, methods and computer program products for automatically ingesting and filing documents in a database having a plurality of file locations. An electronic file having one or more documents is received. For each document in the received file, text data is identified and used to generate a plurality of suggested file locations for the received documents. Machine learning systems may be used to enhance the accuracy of suggested file locations.