Automated Email Classification System for Human Machine Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users face challenges in managing large volumes of incoming electronic messages, as they need to determine which messages require more or less attention, time, or priority, with existing tools failing to effectively differentiate between human-generated and machine-generated content.

Innovation Solution

A computer system and method that employs both offline and online phases to identify whether a message is from a human or a machine, using local resources and network-accessible information, and provides users with the results to prioritize and automatically extract data from messages accordingly.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If users manually review each received message to determine priority and content, then message handling accuracy is maintained, but time consumption increases significantly due to large message volumes

Engineering Contradiction:
Improvemessage handling accuracyVSAvoidtime consumption
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent introduces an automated message analysis system that acts as an intermediary between incoming messages and user review. This system extracts entities, classifies messages by type and priority, and presents structured information to users, thereby maintaining accuracy while significantly reducing the time users must spend manually reviewing each message.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the manual mechanical process of reading and analyzing each message with an automated computational system that uses entity extraction, classification algorithms, and structured data presentation to perform the same analytical function at scale, reducing time consumption while maintaining or improving accuracy.

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

2Ease of operation

If users apply uniform processing to all messages, then processing simplicity is maintained, but efficiency decreases because different message types require different handling approaches

Engineering Contradiction:
Improveprocessing simplicityVSAvoidmessage processing efficiency
Core Design Contradiction:
Ease of operationVSProductivity

Solution Approach 1:

The patent applies local quality by treating different message types differently based on their classified categories. The system extracts and prioritizes different entities based on message type (e.g., financial data for billing messages, appointment details for calendar messages), allowing optimized processing for each message category while maintaining overall system simplicity through automated classification.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent changes processing parameters dynamically based on message classification. Different extraction rules, priority levels, and handling procedures are applied depending on the message type identified by the system, enabling efficient differentiated processing without requiring complex manual decision-making for each message.

Inventive Principle:
Principle #35Parameter changes

3Speed

If automated data extraction is applied to all messages, then data processing speed increases, but accuracy decreases for human-generated messages that require contextual understanding

Engineering Contradiction:
Improvedata processing speedVSAvoiddata extraction accuracy
Core Design Contradiction:
SpeedVSMeasurement precision

Solution Approach 1:

The patent applies partial automation by performing automated data extraction only on machine-generated messages where rules-based extraction is effective, while preserving manual review for human-generated messages that require contextual understanding. This selective application of automation maintains accuracy for complex messages while achieving speed benefits for suitable candidates.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The patent segments the message processing workflow into automated extraction for machine messages and manual review for human messages, allowing each segment to use the most appropriate method for its specific message type, thereby optimizing both speed and accuracy for different message categories.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS10778618B2Method and system for classifying man vs. machine generated e-mail
Publication Date: 2020.09.15 YAHOO ASSETS LLC
  • US10778618B2 patent drawing
  • US10778618B2 patent drawing
  • US10778618B2 patent drawing

AI summary

A computer system, computer program product, and computer-implemented method for communicating electronic messages over a communication network coupled thereto are provided. The computer system comprises a network interface for receiving messages sent over the network and addressed to a user of the computer system; and computer executable electronic message processing software. The software comprises instructions for directing the computer system to receive a message over the network, and to identify whether a sender of the received electronic message is a human or a machine. The identifying includes first and second phases of operation. The first phase includes an offline phase employing information and activities resident on the computer system. The second phase includes an online phase employing resources remotely accessible over the network. The software further includes instructions for providing the user with the results of the identification as human or machine; and for performing automatic data extraction from the message if the message was identified to be from a machine.