Ontology-Based Communication Data Analytics

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current automated data processing systems lack an effective method to analyze and interpret communication data across various domains, particularly in understanding linguistic patterns and relationships, which hinders the extraction of meaningful insights from customer interactions.

Innovation Solution

The development of an ontology-based system that processes communication data to identify terms, relations, and patterns, using machine learning to create a structural representation of language elements and their relationships, allowing for refinement and application in specific business domains.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated data processing systems are used to analyze communication data, then processing speed is improved, but the ability to understand linguistic patterns and relationships deteriorates

Engineering Contradiction:

Improveprocessing speedVSAvoidlinguistic pattern understanding

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent introduces an ontology as an intermediary layer between automated data processing and communication data analysis. The ontology provides structured knowledge representations (classes, properties, relationships) that enable automated systems to understand linguistic patterns and domain-specific meanings, thereby maintaining both processing speed and linguistic comprehension capability

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs preliminary action by pre-defining ontological structures, classes, and relationships before processing communication data. This preparatory framework allows the automated system to quickly map and interpret linguistic patterns during actual data processing without sacrificing understanding accuracy

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If ontology structures are created to represent language elements, then linguistic understanding is improved, but system complexity increases

Engineering Contradiction:

Improvelinguistic understandingVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The ontology system is segmented into distinct modular components: classes representing language elements, properties describing characteristics, and relationships defining connections. This segmentation allows the complex linguistic understanding task to be broken down into manageable, independently developable modules that can be processed and maintained separately

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The ontology structure serves multiple functions simultaneously: it represents language elements, defines their relationships, enables pattern recognition, and provides a framework for automated reasoning. This multi-functionality reduces the need for separate systems for each task, thereby managing overall system complexity while enhancing linguistic understanding

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Adaptability or versatility

If machine learning is used to create ontologies, then adaptability to specific domains is improved, but processing time increases

Engineering Contradiction:

Improvedomain adaptabilityVSAvoidontology creation time

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The machine learning process incorporates feedback mechanisms where the system learns from training data, evaluates its ontology creations, and iteratively improves its domain-specific representations. This feedback loop enables the system to adapt to specific domains more efficiently by learning from errors and successes, reducing the overall time required for accurate ontology creation

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs preliminary action by pre-training machine learning models on general language data before domain-specific adaptation. This preliminary training provides a head start, reducing the time needed for domain-specific ontology creation while maintaining high adaptability to target domains

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS9477752B1Ontology administration and application to enhance communication data analytics

Publication Date: 2016.10.25 VERINT SYST INC

AI summary

A method for developing an ontology for practicing communication data, wherein the ontology is a structural representation of language elements and the relationship between those language elements within the domain, includes providing a training set of communication data and processing the training set of communication data to identify terms within the training set of communication data, wherein a term is a word or short phrase. The method further includes utilizing the terms to identify relations within the training set of communication data, wherein a relation is a pair of terms that appear in proximity to one another. Finally, the terms in the relations are stored in a database.