Semantic Entity Similarity Calculation for Automated Email Organization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing email organization methods, such as conversation grouping and labeling, require manual input and can be cumbersome, especially when retrieving information from cluttered inboxes or when messages lack explicit rules or reply functions, making it difficult to find related messages.

Innovation Solution

A system that selects and parses semantic entities from documents to calculate similarity levels based on co-occurrence frequencies and weighted inverse-document-frequency (IDF) values within sentences and paragraphs, allowing for automated grouping of related messages.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual rules or labels are used to organize emails, then organization accuracy is improved, but user effort and time consumption increase

Engineering Contradiction:

Improveorganization accuracyVSAvoiduser effort and time consumption

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system automatically extracts semantic entities and calculates similarities between emails without requiring manual user input. The automated entity extraction and similarity calculation perform the organization function that would otherwise require manual rule application or labeling by the user.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical processes (user manually applying rules or labels) with an automated computational system that uses semantic entity extraction and similarity calculation algorithms to organize emails automatically.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If conversation grouping is used to organize emails, then related messages are grouped together, but it fails when messages lack explicit reply functions or rules

Engineering Contradiction:

Improvegrouping capabilityVSAvoidretrieval reliability

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system changes the parameter for organizing emails from explicit structural indicators (reply functions, conversation threads) to semantic meaning-based parameters (entity types, co-occurrence frequencies). This allows the system to handle emails that lack explicit reply functions by analyzing the semantic content and relationships between entities.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If semantic entity extraction is performed on entire documents, then entity identification is comprehensive, but processing time and computational complexity increase

Engineering Contradiction:

Improveentity identification accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent segments the document processing into extracting semantic entities from individual sentences or paragraphs rather than processing the entire document at once. This segmentation allows for more efficient processing while maintaining comprehensive entity identification accuracy.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS8762375B2Method for calculating entity similarities

Publication Date: 2014.06.24 GENESEE VALLEY INNOVATIONS LLC

AI summary

One embodiment of the present invention provides a system for estimating a similarity level between semantic entities. During operation, the system selects two or more semantic entities associated with a number documents. The system subsequently parses the documents into sub-parts, and calculates the similarity level between the semantic entities based on occurrences of the semantic entities within the sub-parts of the documents.