Clustering Engine for Unsupervised Document Tagging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems face inefficiencies and delays in customer support due to the disconnect between product development, service functions, and customer support, leading to increased costs, reputational damage, and reduced customer satisfaction, as well as the inability to effectively process and respond to product complaints and inquiries in a timely manner.
Innovation Solution
A Product/Service Knowledge Database (PKD) is created to cluster and manage documents, problem metadata, solution metadata, and recommendation data, enabling semi-supervised tagging and navigation, and cross-learning, which facilitates automated customer support and product design improvements by integrating with a Customer Support System (CSS) to provide efficient problem intake, diagnosis, and solution recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If manual processing of customer support inquiries is used, then human intermediaries can provide personalized assistance, but response time increases and costs increase
Solution Approach 1:
The patent introduces an automated content processing system that acts as an intermediary between customer inquiries and human support agents. This system clusters similar inquiries together and identifies relevant resolution content automatically, reducing the manual workload and response time while maintaining support quality through a hybrid automated-human approach
Solution Approach 2:
The system enables self-service by automatically clustering customer inquiries and matching them with relevant resolution content from knowledge bases or documentation. This allows the system to handle routine inquiries autonomously, reducing dependency on human intermediaries for standard issues while freeing them to handle complex problems
2Reliability
If more human intermediaries are hired to handle customer support, then customer service quality improves, but operational costs increase
Solution Approach 1:
The patent segments customer inquiries into clusters based on similarity, allowing the system to handle groups of related inquiries together. This segmentation enables more efficient resource allocation, where automated systems handle routine clustered inquiries and human agents focus on complex or unusual cases, improving service quality while controlling costs
Solution Approach 2:
The automated content processing system serves multiple functions: it clusters inquiries, identifies relevant content, generates summaries, and prepares responses. This multi-functional system replaces multiple specialized roles, maintaining service quality while reducing the need for numerous human intermediaries and associated costs
3Productivity
If automated content processing is implemented, then response time decreases and productivity increases, but the system complexity increases
Solution Approach 1:
The system performs preliminary actions by pre-clustering content and inquiries, and pre-identifying potential matches before actual customer interactions occur. This advance preparation reduces processing time during live interactions and improves productivity, while the complexity is managed through systematic pre-processing rather than complex real-time algorithms
Data Source
AI summary
The present invention relates to a computer-based system for supporting Product Customer Support Systems by means for parameter-free and fully unsupervised: clustering of a selected set documents (e.g., based on a query from some database) with unknown ontology (e.g., cases from Customer Support System); building a taxonomy for sets of documents with unknown ontology/taxonomy; enabling a semi-supervised tagging/navigation/recommendations for documents and cross-learning using auxiliary sources (e.g., linking other fields/metadata in Customer Support Systems such as Knowledge DataBase).