Ontology-Based Relation Tagging for Communication Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automated data processing systems face challenges in effectively interpreting and analyzing communication data, such as customer service interactions, due to the complexity of human communication and sentiment interpretation, particularly in multi-language contexts.
Innovation Solution
The development of an ontology-based system that identifies and tags meaningful relations in communication data through a process involving term extraction, relation scoring, and conflict resolution, allowing for the creation of an ontological structure that enhances data analysis and business insights.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If automated data processing systems attempt to interpret and analyze communication data in multi-language contexts, then the ability to extract business insights is improved, but the complexity of sentiment interpretation and human communication analysis increases
Solution Approach 1:
The patent introduces an ontology as an intermediary layer between raw communication data and analysis results. The ontology provides a structured framework of concepts, relations, and rules that mediates the complex task of multi-language sentiment interpretation, making the system more manageable and adaptable without proportionally increasing complexity
Solution Approach 2:
The ontology is designed as a universal framework that can handle multiple languages and communication types through a single unified structure. This multi-functional approach allows the system to process diverse communication data (audio, text, chat) across different languages using the same ontological relations and rules, improving adaptability without requiring separate systems for each language or modality
2Reliability
If the system tags all possible relations in communication data, then the completeness of data analysis is improved, but the computational resources and processing time increase
Solution Approach 1:
The system dynamically adjusts scoring parameters and thresholds based on the specific communication data being analyzed. By changing parameters such as relation scoring weights, confidence thresholds, and tagging priorities, the system can optimize between completeness and processing speed for different analysis scenarios, allowing flexible trade-offs between reliability and productivity
Solution Approach 2:
The patent implements a two-stage approach where high-confidence relations are tagged first (partial action), and lower-confidence relations are processed selectively or skipped based on resource availability. This allows the system to achieve sufficient completeness for critical relations without expending excessive computational resources on all possible relations, maintaining an optimal balance between thoroughness and efficiency
3Measurement precision
If the system resolves conflicts between competing relations through predefined criteria, then the accuracy of tagged relations is improved, but the complexity of conflict resolution rules increases
Solution Approach 1:
The conflict resolution mechanism applies different scoring criteria and resolution rules based on the local context of each relation. Instead of using a single complex set of global rules, the system evaluates conflicts using localized parameters such as relation strength, contextual relevance, and positional information specific to each conflict instance, reducing overall system complexity while maintaining high accuracy
Data Source
AI summary
Systems, methods, and media for developing ontologies and analyzing communication data are provided herein. In an example implementation, the method includes: identifying terms in in a set of communication data; identifying a list of possible relations of the identified terms; scoring the possible relations according to a set of predefined merits; ranking the possible relations into a list of possible relations in descending order according to their score; and tagging relations in the set of communication data. The relations may be tagged by identifying the possible relations in the communication data in order corresponding with the list of possible relations. The possible relations that have lower rankings that conflict with higher ranking relations are not tagged. The conflicts may be determined by a predefined set of conflict criteria.