Customer Inquiry Topic Detection Using Keyword Graph Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems lack efficient mechanisms for identifying new or trending topics in customer inquiries, leading to inefficient troubleshooting of computing and software issues due to the complexity of reviewing and categorizing large volumes of textual feedback, which requires substantial time and computing resources.
Innovation Solution
A data processing system utilizing natural language processing, statistical inferences, and graph search methodologies to detect trending keywords, cluster inquiries, and generate real-time alerts for new or surging topics by analyzing non-structured text data from diverse sources, optimizing data ingestion and storage, and employing a graph search process to group inquiries into distinct clusters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If employees review and analyze customer inquiries individually, then analysis accuracy is improved, but time consumption and labor requirements increase significantly
Solution Approach 1:
The patent replaces manual mechanical review processes with automated natural language processing systems. The system uses NLP algorithms to automatically extract keywords, detect trends, and cluster inquiries, eliminating the need for employees to read and analyze each inquiry individually while maintaining accurate analysis through computational methods
Solution Approach 2:
The system performs self-service analysis by automatically processing customer inquiries without human intervention. The NLP system independently extracts insights, identifies trends, and generates notifications, allowing the system to serve itself rather than requiring employees to manually review and categorize each inquiry
2Measurement precision
If comprehensive review of all customer inquiries is performed, then topic identification accuracy is improved, but computing resources and complexity increase
Solution Approach 1:
The patent extracts only the essential information from customer inquiries by using NLP to identify and isolate key keywords and phrases. Instead of processing every word and sentence in detail, the system extracts meaningful terms that indicate trends and issues, reducing computational complexity while maintaining accurate topic identification
Solution Approach 2:
The system segments the analysis process into distinct stages: keyword extraction, frequency comparison, trend detection, and clustering. By dividing the complex task of comprehensive review into manageable segments, the system reduces overall computational complexity while maintaining the ability to identify accurate topics through systematic processing
3Speed
If real-time analysis of customer inquiries is implemented, then response speed is improved, but computational resource consumption increases
Solution Approach 1:
The patent applies partial action by processing only the necessary portions of customer inquiries - specifically extracting and analyzing key keywords rather than processing every aspect of each inquiry in full detail. This selective processing enables real-time response while reducing computational resource consumption compared to comprehensive analysis of all inquiry data
Data Source
AI summary
A system and method for detecting trending topics in customer inquiries includes retrieving customer inquiries from a plurality of data sources for a target time window and reference time windows and detecting trending keywords in the target time window as compared to keywords in the reference time windows. Responsive to detecting the trending keywords, customer inquiries in the target time window that include one or more of the trending keywords are collected and a weight is measured for each collected customer inquiry based on weights of detected trending keywords in each collected customer inquiry. A connection graph is generated for the detected trending keywords and the collected customer inquiries. The detected trending keywords are then clustered into a plurality of trending topics based on the connection graph, and the trending topics are ranked based on the measured weights of the collected customer inquiries associated with each trending topic.