Machine Learning Data Extraction from Electronic Communications

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional data extraction technologies, such as OCR, struggle with complex layouts in electronic communications, lack contextual understanding, and require significant processing power, making them inefficient and prone to errors.

Innovation Solution

A computer-implemented method and system using machine learning to extract data from electronic communications by training a machine learning model with labeled training data, processing electronic communications to remove and replace tags, and analyzing the processed data to output predicted values for defined categories.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If OCR techniques are used to extract data from electronic communications, then text can be converted into machine-encoded format, but the system struggles with complex layouts and requires significant processing power

Engineering Contradiction:

Improvedata extraction efficiencyVSAvoidprocessing power consumption

Core Design Contradiction:

ProductivityVSUse of energy by moving object

Solution Approach 1:

The patent replaces traditional OCR mechanical processing with a machine learning-based system that uses trained models to directly analyze and extract data from electronic communications. The ML model processes the communication content intelligently, avoiding the heavy computational overhead of conventional OCR while handling complex layouts more effectively.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Loss of information

If conventional OCR technology is used, then text conversion is achieved, but the system lacks contextual understanding and exposes sensitive information

Engineering Contradiction:

Improvecontextual understandingVSAvoidsensitive information exposure

Core Design Contradiction:

Loss of informationVSObject-affected harmful factors

Solution Approach 1:

The patent changes the processing parameters by using machine learning models that understand contextual relationships in the data. The ML approach analyzes the semantic meaning and structure of electronic communications, enabling contextual understanding while controlling access to sensitive information through intelligent processing rather than simple text conversion.

Inventive Principle:

Principle #35Parameter changes

3Adaptability or versatility

If hard-coded heuristics are used for data extraction, then simple patterns can be recognized, but the system is difficult to update and improve

Engineering Contradiction:

Improvemodel update capabilityVSAvoidsystem maintenance complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements a dynamic system where the machine learning model can be retrained and updated with new data. Unlike static hard-coded heuristics, the ML model adapts to new patterns and requirements through continuous learning, making the system flexible and easy to improve without complex maintenance procedures.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS12288151B2Using machine learning to extract information from electronic communications

Publication Date: 2025.04.29 FETCH REWARDS

AI summary

Systems and methods for using machine learning to extract data from electronic communications are disclosed. According to certain aspects, a machine learning model is trained on a set of tasks using a set of training data. An electronic communication indicating a purchase of a product and/or service is processed to generate augmented text that is input into the machine learning model. After analyzing the augmented text, the machine learning model outputs a set of predicted values for a set of defined categories, which an entity may use for various purposes such as to apply digital rewards to user accounts.