Automated Document Classification and Cloud Storage System

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The manual sorting and storage of documents received through various channels, such as email attachments or camera captures, is time-consuming and often results in disorganized storage, making it difficult to locate documents when needed.

Innovation Solution

A method and apparatus that automatically classify documents based on extracted features, associating them with known document types and storing them in dedicated locations within a cloud storage system, using a processor to define document types, extract features, and compare them to feature information for accurate classification and storage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual sorting and storage of documents is performed, then documents can be stored in a storage system, but the process is time-consuming and documents are not stored in a logical or useful manner

Engineering Contradiction:
Improvedocument storage efficiencyVSAvoidtime for manual sorting
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The system performs automatic document classification and storage without requiring user intervention. The processor automatically extracts features from documents, compares them to known document types, and stores documents in appropriate locations, enabling the system to serve itself rather than requiring manual user sorting.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual sorting process with an automated computational system. Instead of users physically sorting documents, the system uses feature extraction and comparison algorithms to automatically classify and organize documents, substituting human mechanical action with automated information processing.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If manual sorting of documents is performed, then documents can be transferred to storage, but documents cannot be located when needed due to disorganized storage

Engineering Contradiction:
Improvedocument retrieval easeVSAvoiddocument organization information
Core Design Contradiction:
Ease of operationVSLoss of information

Solution Approach 1:

The system performs preliminary classification and organization of documents before they are stored. By automatically categorizing documents into known document types and storing them in dedicated locations in advance, the system ensures documents are easily locatable when needed, eliminating the need for subsequent search and reorganization.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system uses feature extraction and comparison to create a classification feedback mechanism. Documents are analyzed against known document type features, and the classification results feed into the storage process, ensuring documents are organized according to their identified characteristics for future retrieval.

Inventive Principle:
Principle #23Feedback

3Extent of automation

If automatic document classification is implemented, then documents can be stored efficiently by type, but the system complexity increases due to feature extraction and comparison processes

Engineering Contradiction:
Improveautomatic document classificationVSAvoidsystem complexity for feature processing
Core Design Contradiction:
Extent of automationVSDevice complexity

Solution Approach 1:

The automatic classification system is segmented into distinct functional components: feature extraction module, comparison module, and storage module. This segmentation allows each component to perform its specific function independently, managing complexity by dividing the overall automated classification task into manageable segments.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS9870420B2Classification and storage of documents
Publication Date: 2018.01.16 GOOGLE LLC
  • US9870420B2 patent drawing
  • US9870420B2 patent drawing
  • US9870420B2 patent drawing

AI summary

A method includes defining a plurality of known document types, obtaining a collection of previously classified documents that are each associated with one of the known document types, and extracting features from each document from the collection of previously classified documents to define feature information. The method also includes obtaining a subject document that is associated with a user, extracting one or more features from the subject document, comparing the one or more features from the subject document to the feature information, associating the subject document with one of the known document types based on the comparison, and transmitting the document to a cloud storage system for storage in a dedicated storage location that is associated with the user and contains only documents of the respective known document type that is associated with the subject document.