Unified Data Extraction from Invoices and Contracts

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Companies face challenges in managing and comparing data from different types of documents with varying structures, such as financial and legal documents, due to compartmentalization of data management tools and the lack of a common agreement on classification, making it difficult to check contractual obligations and track expenditures under complex pricing arrangements.

Innovation Solution

A computer-implemented method and system that retrieves and extracts data from documents with different structures, using translation tables to order the data into structured formats, and employs natural language processing and machine learning algorithms to identify matching entities and generate reports based on client specifications.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If separate management tools are used for different document types (classification engine for products, contract management systems for contracts, CRM for sales), then each department can manage its specific data, but data becomes compartmentalised and cannot be centrally managed or compared

Engineering Contradiction:

Improvedepartmental data management capabilityVSAvoiddata compartmentalisation

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent merges multiple separate document management systems into a single unified platform that can handle various document types (products, contracts, sales) through a common interface and data structure, eliminating data silos while maintaining departmental management capabilities

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system creates a universal document management framework that serves multiple functions across different departments and document types, using translation tables and standardized data structures to enable centralized management of diverse data while maintaining adaptability to specific departmental needs

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Productivity

If translation tables and standardized data structures are implemented to enable centralized data management, then data from different document types can be compared and analyzed, but the processing complexity and time required to extract and normalize data increases

Engineering Contradiction:

Improvedata comparison and analysis capabilityVSAvoiddata extraction and normalization time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-defining translation tables and standardized data structures before data processing begins, allowing for automated mapping and normalization of various document types into a common format, thereby reducing the time required during actual data extraction and comparison operations

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

Translation tables serve as intermediaries between different document formats and the standardized internal data structure, automatically mapping fields from various source formats to the target structure, which streamlines the normalization process and reduces manual intervention time

Inventive Principle:

Principle #24Intermediary (Mediator)

3Measurement precision

If manual methods are used to check contractual obligations and compare data from different documents, then data accuracy can be maintained, but the process is difficult and time-consuming

Engineering Contradiction:

Improvedata accuracyVSAvoidmanual data checking time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system enables self-service by automatically extracting, normalizing, and comparing data from various documents using predefined translation tables and processing rules, allowing the system to perform data validation and comparison tasks autonomously while maintaining accuracy through structured data mapping

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical data checking processes with automated computational systems that use translation tables and standardized data structures to extract, map, and compare data from different document types, significantly reducing time while maintaining or improving accuracy through systematic processing

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12001446B2System and method for extracting data from invoices and contracts

Publication Date: 2024.06.04 THINKING MASCH SYST LTD

AI summary

A data processing system and corresponding method are presented. The system includes a communication module to retrieve a first document and a second document; a first database to store the first and second documents; and a processor. The processor extracts first data from the first document, orders the first data into a first data structure using a set of translation tables. The processor also extracts second data from the second document, orders the second data into a second data structure using the set of translation tables. The first data structure and the second data structure have a first and a second format, respectively. The first data and the second data comprise a plurality of entities, and the processor is configured to compare entities from the first data structure and the second data structure to identify matching entities.